Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/bodangren/git-workflow/agents-mdgit clone --depth 1 https://github.com/bodangren/git-workflowWhat 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 | $0.00761 | $0.00761 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
git-workflow AGENTS.md scanned grade A with 0 findings 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 2d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgenticDev Agent Guide
This project uses AgenticDev, a modular, spec-driven development methodology. The workflow is broken down into several discrete skills located in the skills/ and .claude/skills/ directories.
Core Philosophy
- Specs as Code: All specification changes are proposed and approved via Pull Requests.
- Just-in-Time Context: Use the
doc-indexerskill to get a real-time map of all project documentation. - Sprint-Based: Work is organized into GitHub Milestones and planned via the
sprint-plannerskill. - Atomic Issues: Implementation is done via atomic GitHub Issues, which are executed by the
issue-executorskill. - Hybrid Architecture: LLM executes workflow steps with strategic reasoning, helper scripts automate repetitive tasks.
Available Skillsets
Each skill contains comprehensive documentation in SKILL.md (50-262 lines) explaining purpose, workflow, and error handling. Helper scripts are located in each skill's scripts/ directory.
skills/skill-lister/: For listing all available skills and their descriptions.skills/project-init/: Initialize AgenticDev directory structure in new projects. Creates docs/specs and docs/changes directories.skills/project-migrate/: Migrate existing (brownfield) projects with established documentation to AgenticDev structure. Intelligently discovers, categorizes, and migrates documentation while preserving content, adding frontmatter, and maintaining git history.skills/prd-authoring/: Guide early-stage project planning through Product Requirements Documents (PRDs). Manages the complete workflow from initial product briefs through market research, PRD creation, validation, and epic decomposition. Bridges the gap between project ideas and spec-driven development with data-driven requirements and measurable success criteria.skills/doc-indexer/: Scan and index project documentation for just-in-time context discovery. Provides a map of all available docs without loading full content.skills/spec-authoring/: Create and refine specification proposals via Spec PR workflow. Supports both proposing new specs and updating based on review feedback.skills/sprint-planner/: Plan sprints by creating GitHub milestones and issues from approved specs. Automates issue creation while LLM guides strategic planning.skills/issue-executor/: Execute development workflow for a single issue. Loads full context (specs, retrospective, doc index) and creates feature branch.skills/change-integrator/: Integrate completed changes post-merge. Moves specs to source-of-truth, updates retrospective, and cleans up branches.skills/doc-validator/: Validate that Markdown files are in standard locations. Scans for .md files outside of predefined allowed directories and outputs warnings to prevent documentation sprawl.skills/agent-integrator/: Create or update this AGENTS.md file. Uses marker-based idempotent updates to register AgenticDev capabilities.
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.
- 2d ago First seen · 39 lines · 761 tokens per session scan A d9b3c4e5570e
git-workflow AGENTS.md is an instructions file published in the GitHub repository bodangren/git-workflow (11 stars, last pushed 9mo ago), licensed MIT. It adds 761 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Table-GitHub-Capability-Router AGENTS.md
Instructions for duoduoler-ops/Table-GitHub-Capability-Router: This is the canonical repository instruction file. Client-specific compatibility files must point here instead of duplicating these rules.
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
wiki_ticket_sdd CLAUDE.md
Instructions for SpillwaveSolutions/wiki_ticket_sdd, covering acme platform, work tracking policy and work taxonomy.
super-backlog CLAUDE.md
Instructions for adam-s-k-i/super-backlog: This project uses the combined Backlog.md + Superpowers workflow. Read the integration block in AGENTS.md (section between SUPER-BACKLOG markers) and follow it. Tasks are managed exclusively through the backlog CLI.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
bankan CLAUDE.md
Instructions for stilero/bankan, covering claude.md, what this is, commands, architecture and server modules (server/src/).