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 skills/richfrem/agent-plugins-skills/context-bundlernpx skills add richfrem/agent-plugins-skills --skill context-bundlergit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/skills/richfrem/agent-plugins-skills/context-bundler)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/context-bundler"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/context-bundler.svg" alt="Measured on agentmods" 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 | $0.00095 | $0.01718 |
| Opus 5 | $0.00048 | $0.00859 |
| Sonnet 5 | $0.00019 | $0.00344 |
| Haiku 4.5 | $0.00010 | $0.00172 |
Grade A, and why
context-bundler 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependencies
This skill requires Python 3.8+ and standard library only. No external packages needed.
Context Bundler Skill 📦
Overview
This skill centralizes workflows for compiling codebase files, documentation, and instructions into portable payloads (.md for AI chat UIs or .zip for offline/agent handoffs).
context-bundler supports 4 Execution Modes:
- Standard Bundle Mode: Custom interactive selection of files/directories for general review or context sharing.
- Persona-Driven Review / Handoff Mode: Injects specialized review or delegation persona prompts (
prompt.md) ahead of codebase files. - Monorepo Segmented Mode: Full monorepo context packaging partitioned by domain (
/skills,/agents,/scripts,/docs). - Multi-Persona Fan-Out Mode: Packages the same target content against multiple persona templates in one pass, producing one bundle per persona for parallel adversarial dispatch. This is the mechanism
graph-planning-superpowers-policy.md§2.2-2.3 refers to for Phase 1 plan review.
🎭 Persona Template Library (assets/templates/)
When bundling context for external models, sub-agents, or human reviews, select or recommend a template from assets/templates/:
1. Security & Quality Review Personas
adversarial-security-auditor.md: OWASP Top 10, auth bypasses, injection vectors, exploit scenarios, CVSS risk ratings.refactoring-quality-specialist.md: DRY violations, code smells, cyclomatic complexity reduction, before/after code diffs.compliance-standards-reviewer.md: Project conventions, 20-line purpose headers, ADR compliance, type annotations.
2. Architecture & Design Planning Personas
structural-architecture-reviewer.md: C4 model, SOLID principles, coupling, interface abstraction leaks, component boundaries.plan-critique-reviewer.md: Stress-tests implementation plans, unstated dependencies, execution friction, rollback mechanisms.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- acceptance-criteria.md 949 B
- assets/resources/file-manifest-schema.json 54 B
- assets/resources/file-manifest.json 47 B
- assets/templates/adversarial-security-auditor.md 60 B
- assets/templates/agent-task-delegator.md 52 B
- assets/templates/compliance-standards-reviewer.md 61 B
- assets/templates/docs-synthesis-specialist.md 57 B
- assets/templates/plan-critique-reviewer.md 54 B
- assets/templates/refactoring-quality-specialist.md 62 B
- assets/templates/structural-architecture-reviewer.md 64 B
- assets/templates/tdd-contract-reviewer.md 53 B
- evals/evals.json 718 B
- evals/results.tsv 301 B
- fallback-tree.md 1.3 KB
- requirements.in 21 B
- requirements.txt 22 B
- scripts/bundle_zip.py 30 B runs code
- scripts/bundle.py 26 B runs code
- scripts/manifest_manager.py 36 B runs code
- scripts/path_resolver.py 33 B runs code
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 · 135 lines · 95 tokens per session scan A 5403559371d5
context-bundler is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 95 tokens to every session and 1,718 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
review-pr
Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback.
paper-fetch
Use whenever the user wants to obtain, download, or fetch a paper's PDF — given a DOI, an arXiv id, a paper title, a citation, or a list of DOIs. Trigger on phrases like "download this paper", "find the PDF for [DOI]", "grab me the [Nature/bioRxiv/arXiv] paper on X", "get the open-access version", "I need this…
ship-it-or-fix-it
Oracle-frozen Builder and independent-Judge convergence cycle. Load ONLY when the operator explicitly sets Governance Dial G2 for the task, or explicitly names this skill or an active work unit already running it. Never auto-activate on task class, such as security, auth, or payments. If a task seems to warrant G2 and…
test-verification
Requires behavioral, failure-path, and durable-seam evidence for tests and review. Use when writing tests, reviewing test coverage, assessing behavioral test quality, or accepting high-risk behavior on test evidence.
atelier-setup
Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.
code-review
Perform comprehensive code reviews covering bugs, style, performance, security, and best practices. Use this skill when the user mentions: review my code, check this code, code review, find bugs, improve code, refactor suggestions, security audit, performance optimization, code quality, static analysis.