Borrowing it
Nothing to install: this file belongs to jamditis/claude-skills-journalism. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jamditis/claude-skills-journalism/master/AGENTS.mdgit clone --depth 1 https://github.com/jamditis/claude-skills-journalismWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/jamditis/claude-skills-journalism/agents-md)<a href="https://agentmods.dev/instructions/jamditis/claude-skills-journalism/agents-md"><img src="https://agentmods.dev/badge/instructions/jamditis/claude-skills-journalism/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jamditis/claude-skills-journalism/agents-md"><img src="https://agentmods.dev/badge/instructions/jamditis/claude-skills-journalism/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05607 | $0.05607 |
| Opus 5.5 | $0.02243 | $0.02243 |
| Sonnet 5.5 | $0.01121 | $0.01121 |
| Haiku 4.5 | $0.00561 | $0.00561 |
Grade B, and why
claude-skills-journalism AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
No AI attribution in commits, PR bodies, issues, docs, or code. `.claude/settings.json` sets `attribution.sessionUrl` to false and blanks `attribution.commit` and `attribution.pr`, which stops Claude Code from appending This is a copy
89% identical to claude-skills-journalism CLAUDE.md — 428 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent skills collection
Project: Journalism skills maintenance
Bug-fixing workflow
When a bug is reported, don't immediately attempt to fix it. Instead:
- Establish the failure with the cheapest faithful evidence: an existing test, a focused command, a log, or a new failing test
- Fix the cause, not the symptom
- Prove the fix with the same evidence. Keep a new regression test only when the bug is likely to recur or affects an important contract, non-obvious logic, or high-impact behavior
Collection of Claude Code and Codex skills for journalism, media, academia, and technical workflows.
Project overview
This repo contains modular instruction sets that extend supported coding agents for specialized tasks. Each skill directory contains domain knowledge, workflows, templates, and best practices.
Directory structure
Packages use .claude-plugin/plugin.json. Codex supports standards-based skill
installs and a verified legacy-compatible journalism-core package route. Each
stable skill has Codex UI metadata. The repository does not ship native Codex
plugin manifests.
claude-skills-journalism/
├── AGENTS.md # Canonical project instructions
├── CLAUDE.md # Claude Code import for AGENTS.md
├── README.md # User documentation
├── LICENSE
│
├── hooks/ # Automated workflow checks (16 hooks)
│ ├── ap-style-check.md # Writing: AP Style violations
│ ├── ai-slop-detector.md # Writing: AI patterns
│ ├── accessibility-check.md # Writing: Alt text, headings
│ ├── copywriting-preflight.md # Writing: Intent interview before drafting
│ ├── source-attribution-check.md # Verification: Unattributed claims
│ ├── verification-reminder.md # Verification: Fact-check prompt
│ ├── data-methodology-check.md # Verification: Methodology docs
│ ├── source-diversity-check.md # Editorial: Source diversity
│ ├── legal-review-flag.md # Editorial: Defamation risk
│ ├── pre-publish-checklist.md # Editorial: Pre-publish reminder
│ ├── deadline-tracker.md # Editorial: Deadline surfacing
│ ├── archive-reminder.md # Preservation: Archive URLs
│ ├── one-way-door-check.md # Development: Block irreversible decisions
│ ├── bug-report-detector.md # Development: Detect bug reports
│ ├── pre-commit-review.md # Development: Review staged diff before commit
│ └── no-ai-attribution.md # Development: Block AI attribution in commits, PRs, and comments
│
├── # Plugin: journalism-core (16 skills, v1.7.0), registered in marketplace.json
├── journalism-core/
│ ├── .claude-plugin/plugin.json
│ ├── README.md
│ └── skills/
│ ├── ai-writing-detox/ # Eliminate AI writing patterns
│ ├── crisis-communications/ # Breaking news, rapid verification
│ ├── data-journalism/ # Data analysis, federal-data currency, AI-assisted-analysis cautions
│ ├── editorial-workflow/ # Assignment tracking, calendars
│ ├── fact-check-workflow/ # Claim verification
│ ├── foia-requests/ # Public records requests
│ ├── interview-prep/ # Interview preparation
│ ├── interview-transcription/ # Recording, transcription, quotes
│ ├── meeting-transcript-actions/ # Notes, decisions, actions, unresolved questions
│ ├── newsletter-publishing/ # Email newsletters, subscribers
│ ├── newsroom-style/ # AP Style enforcement
│ ├── photo-metadata/ # Embed caption, credit, alt text, license in IPTC/EXIF/XMP
│ ├── brazil-records-requests/ # Brazilian LAI requests and appeals
│ ├── social-media-intelligence/ # OSINT, account analysis, platform-API currency
│ ├── source-verification/ # SIFT method, verification, deepfakes/C2PA
│ └── story-pitch/ # Pitch templates
│
├── # Plugin: newsroom-agent-ops (9 skills, v1.0.0), registered in marketplace.json
├── newsroom-agent-ops/
│ ├── .claude-plugin/plugin.json
│ ├── README.md
│ └── skills/
│ ├── chat-mention-triage/ # Team-chat classification without duplicate replies
│ ├── deadline-and-reply-tracking/ # Due dates, reply windows, and next actions
│ ├── document-delivery/ # Editable document and PDF delivery with readback
│ ├── email-request-intake/ # Allowlisted email intake with untrusted-content controls
│ ├── issue-pool-progression/ # Issue progression through release and live checks
│ ├── multi-agent-coordinator/ # Durable coordination, watches, gates, and cleanup
│ ├── record-reconciliation/ # Canonical records and privacy controls
│ ├── scheduled-briefing/ # Source-backed, phone-readable briefings
│ └── unattended-agent-runs/ # Leases, checkpoints, recovery, and resource limits
│
├── # Plugin: research-toolkit (6 skills, v1.1.4), registered in marketplace.json
├── research-toolkit/
│ ├── .claude-plugin/plugin.json
│ ├── README.md
│ └── skills/
│ ├── academic-writing/ # Research and scholarly communication
│ ├── content-access/ # Unpaywall, library databases, paywall bypass
│ ├── digital-archive/ # AI-enriched archives, entity extraction
│ ├── free-apis-catalog/ # Curated free-API catalog with sunset currency notes
│ ├── page-monitoring/ # Change detection, availability tracking
│ └── web-archiving/ # Wayback, Archive.today, evidence preservation
│
├── # Plugin: dev-toolkit (14 skills), registered in marketplace.json
├── dev-toolkit/
│ ├── .claude-plugin/plugin.json
│ ├── README.md
│ └── skills/
│ ├── accessibility-compliance/ # WCAG 2.2, alt text, focus management
│ ├── claude-md-updater/ # Propose scoped project instruction updates
│ ├── context-engineering-fundamentals/ # Preserve instructions, evidence, and state
│ ├── director/ # Explicit top-tier direction and delegation
│ ├── electron-dev/ # Electron security model, packaging
│ ├── mobile-debugging/ # Eruda, vConsole, remote debug
│ ├── one-way-door/ # Block irreversible decisions
│ ├── ponytail-dev/ # Minimal-code implementation with proportional checks
│ ├── python-pipeline/ # Data pipelines (pandas, polars, DuckDB)
│ ├── surface-completeness/ # UI coverage, design compliance, and docs
│ ├── vibe-coding/ # AI-assisted development
│ ├── web-scraping/ # Ethical content extraction
│ ├── web-ui-best-practices/ # Container queries, :has(), view transitions
│ └── zero-build-frontend/ # ESM import maps, htmx, Alpine.js
│
├── # Plugin: okf-wiki (1 skill), registered in marketplace.json
├── okf-wiki/ # Scaffold an Open Knowledge Format knowledge base
│ ├── .claude-plugin/plugin.json
│ ├── SKILL.md
│ ├── spec/SPEC.md # generic OKF spec v1
│ ├── scripts/ # scaffold.py, validate.py, gh-wiki-bootstrap.py
│ ├── templates/ # .claude/ hooks copied into each scaffolded project
│ ├── example/ # a scaffolded OKF wiki of this repo (dogfood + live example)
│ └── tests/ # pytest: scaffold output, hooks, validator rejections
│
├── # Plugin: pdf-design (1 skill), registered in marketplace.json
├── pdf-design/ # PDF reports, proposals, brand system
│ └── templates/ # HTML templates (Democracy Day, etc.)
│
├── # Plugin: video-toolkit (4 skills, v1.0.6), registered in marketplace.json
├── video-toolkit/
│ ├── .claude-plugin/plugin.json
│ ├── README.md
│ └── skills/
│ ├── video-dashboard/ # Interactive transcript and frame analysis
│ ├── video-download/ # Public social-video collection
│ ├── video-frames/ # Frame extraction and vision analysis
│ └── video-transcribe/ # Reproducible Whisper transcription
│
├── # Plugin: web-design-picker (1 skill, v1.0.1), registered in marketplace.json
├── web-design-picker/ # Website directions, review picker, asset handoff
│ ├── .claude-plugin/plugin.json
│ ├── agents/openai.yaml
│ ├── assets/ # Picker, catalog, concept, schema, and favicon sources
│ ├── references/ # Design, accessibility, QA, and delivery guidance
│ ├── scripts/ # Scaffold, build, preview, validate, and package tools
│ └── SKILL.md
│
├── # Plugin: visual-explainer (1 skill), registered in marketplace.json
├── visual-explainer/ # HTML diagrams, data tables, architecture views
│ ├── references/ # CSS patterns, library guides, nav patterns
│ ├── templates/ # Architecture, flowchart, data table templates
│ └── commands/ # Slash command templates
│
├── # Plugin: project-templates-toolkit (4 skills), registered in marketplace.json
├── project-templates-toolkit/
│ ├── .claude-plugin/plugin.json
│ ├── README.md
│ └── skills/
│ ├── goal-progress-bar/ # Evidence-based weighted progress from a JSON tracker
│ ├── project-memory/ # Project instruction generation, 6 project type templates
│ ├── project-retrospective/ # LESSONS.md generation, 4 project type templates
│ └── template-selector/ # Decision tree for picking the right template
│
├── # Plugin: security-toolkit (5 skills, /security-toolkit:hotpatch command), registered in marketplace.json
├── security-toolkit/
│ ├── .claude-plugin/plugin.json
│ ├── README.md
│ ├── commands/hotpatch.md # Slash command: sandboxed pre-install scan + cooldown bypass
│ ├── scripts/hotpatch.example.sh # Reference Linux/bwrap implementation
│ ├── test-fixtures/ # Synthetic malicious tarballs for self-test
│ └── skills/
│ ├── api-hardening/ # Rate limiting, CORS, request throttling, defense-in-depth
│ ├── private-secret-scanning/ # Pinned Gitleaks: staged, push-range, and history scans
│ ├── secure-auth/ # Password hashing, sessions, JWT, OAuth, passkeys
│ ├── security-checklist/ # Pre-deployment OWASP audit
│ └── supply-chain-hardening/ # npm/bun install-time cooldown + sandboxed bypass scan
│
├── # Plugin: autocontext (no skills, hooks/commands/agents), registered in marketplace.json
├── autocontext/ # Cross-session knowledge persistence with skill evolution
│ ├── .claude-plugin/plugin.json
│ ├── agents/ # Lesson-review and evolution agents
│ ├── commands/ # /autocontext:setup, :init, :review, :status, :evolve
│ ├── hooks/ # Capture, validate, and surface lessons across sessions
│ ├── scripts/skill-evolution/ # Fold accumulated lessons back into skill files
│ ├── templates/ # Lesson and archive templates
│ └── tests/
│
├── # Plugin: pdf-playground (8 commands, v1.3.7), registered in marketplace.json
├── pdf-playground/ # Interactive proposal/report/slide builder with live control panel
│ ├── .claude-plugin/plugin.json
│ ├── brands/ # Brand presets
│ ├── commands/ # /proposal, /report, /onepager, /newsletter, /slides, /event, /preview, /update
│ ├── controls/template-maps/ # Live design-editing control wiring
│ ├── hooks/
│ ├── templates/ # Document templates
│ └── skills/ # document-design/ + playground.md (user-invocable entry skill)
│
└── # Plugin: superjawn (13 skills, v2.1.0), registered in marketplace.json
├── # Research-augmented fork of obra/superpowers; standalone, no upstream dependency
├── .claude-plugin/plugin.json
├── README.md
└── skills/
├── brainstorming/ # Research phase: ideation before creative work
├── dispatching-parallel-agents/ # Independent tasks across 2+ agents
├── executing-plans/ # Run a written implementation plan
├── finishing-a-development-branch/ # Decide how to land completed work
├── receiving-code-review/ # Handle review feedback
├── requesting-code-review/ # Verify completed work before merging
├── subagent-driven-development/ # Parallel task execution in one session
├── systematic-debugging/ # Research phase: triage before proposing fixes
├── using-git-worktrees/ # Isolate feature work
├── using-superjawn/ # How to find and use skills
├── verification-before-completion/ # Confirm work is complete before committing
├── writing-plans/ # Multi-step planning before touching code
└── writing-skills/ # Research phase: creating or editing skills
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 428 lines · 5,607 tokens per session scan B a1bf1ab1b782
claude-skills-journalism AGENTS.md is an instructions file published in the GitHub repository jamditis/claude-skills-journalism (432 stars, last pushed today), licensed MIT. It adds 5,607 tokens to every session, about $0.0224 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 89% identical to claude-skills-journalism CLAUDE.md, differing in 428 lines, and is treated as a copy.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.