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 skills add tdimino/claude-code-minoan --skill agents-md-managergit clone --depth 1 https://github.com/tdimino/claude-code-minoanWrote 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/tdimino/claude-code-minoan/agents-md-manager)<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/agents-md-manager"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/agents-md-manager/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/skills/tdimino/claude-code-minoan/agents-md-manager"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/agents-md-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 98 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Tool Misuse · line 114 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 110 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 119 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00117 | $0.01660 |
| Opus 5 | $0.00059 | $0.00830 |
| Sonnet 5 | $0.00023 | $0.00332 |
| Haiku 4.5 | $0.00012 | $0.00166 |
Grade B, and why
agents-md-manager scanned grade B with 2 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 10d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Generate `~/.codex/config.toml` (global) or `.codex/config.toml` (project-scoped): Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Block destructive operations (`rm -rf`, `git push --force`) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md Manager
Create and maintain AGENTS.md files and Codex CLI configuration for any project.
Core Workflow
Determine the mode:
| Mode | When | Script |
|---|---|---|
| Create | New project needs AGENTS.md | scripts/analyze_project.py then write |
| Refresh | Existing AGENTS.md needs audit | scripts/validate_agents_md.py |
| Convert | Migrate from CLAUDE.md | scripts/convert_claude_to_agents.py |
| Config | Generate config.toml | scripts/generate_config_toml.py |
| Rules | Create .rules files | See references/starlark-rules-spec.md |
| Skills | Scaffold .agents/skills/ | scripts/scaffold_codex_skill.py |
1. Project Analysis
Run analysis to detect stack, existing config, and gaps:
python3 ~/.claude/skills/agents-md-manager/scripts/analyze_project.py [project_path]
Output: JSON report with tech stack, commands, directory structure, and Codex artifact inventory (AGENTS.md, config.toml, .rules, .agents/skills/, CLAUDE.md conversion candidates).
2. AGENTS.md Generation
Apply the WHAT/WHY/HOW framework in plain markdown only—no @import syntax, no YAML frontmatter.
Recommended Sections
# Project Name
Brief description.
## Commands
- Dev: `pnpm dev`
- Test: `pnpm test`
- Build: `pnpm build`
- Lint: `pnpm lint`
## Structure
- `/src` — Application source
- `/tests` — Test suites
## Conventions
- [Critical convention 1]
- [Critical convention 2]
## Boundaries
- Always: Run tests before committing
- Ask: Before adding production dependencies
- Never: Modify migration files directly
## Troubleshooting
- [Common issue and fix]
Constraints
- Target under 200 lines per file, under 100 for nested subdirectory files
- Respect 32 KiB limit (
project_doc_max_bytes) - Plain markdown only—no
@import, no YAML frontmatter - Include a "Boundaries" section (Always/Ask/Never) for agent guardrails
- See
references/templates.mdfor project-type-specific templates - See
references/agents-md-spec.mdfor discovery and concatenation rules
What ships with it
12 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.
- README.md 4.7 KB
- references/agents-md-spec.md 3.7 KB
- references/codex-skills-format.md 6.1 KB
- references/config-toml-reference.md 4.0 KB
- references/conversion-mapping.md 7.0 KB
- references/starlark-rules-spec.md 4.3 KB
- references/templates.md 13 KB
- scripts/analyze_project.py 13 KB runs code
- scripts/convert_claude_to_agents.py 9.3 KB runs code
- scripts/generate_config_toml.py 11 KB runs code
- scripts/scaffold_codex_skill.py 5.3 KB runs code
- scripts/validate_agents_md.py 6.1 KB 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.
- 10d ago First seen · 184 lines · 117 tokens per session scan B b93a646c51a5
agents-md-manager is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 1,660 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
manager
A session-to-GitHub tracker that creates, updates, and reads issues across repositories, including their labels, parent epics, and project-board placement.
weekly-retro
A structured weekly retrospective for a one-person business run with AI agents. It gathers evidence from code, project tools, and canonical business files, then records findings and outcomes.
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
corp-doctor
A guided maintenance and setup tool for a Personal Corp system, meaning a business workflow built from AI agents, department repositories, and shared rules. It checks what exists before making changes.
html-draft
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…
idea
Use when capturing ONE new idea the user voices and wants recorded — "save this idea", "I have an idea", "log this idea", "/idea", "idea: ...". Creates a provenance-tracked folder (one folder per idea) in your ideas repo, dedups against an index, optionally mirrors to a GitHub Project view filtered by label:idea. NOT…