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.
git clone --depth 1 https://github.com/damionrashford/media-osWrote 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/agents/damionrashford/media-os/repo-maintainer)<a href="https://agentmods.dev/agents/damionrashford/media-os/repo-maintainer"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/repo-maintainer/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/agents/damionrashford/media-os/repo-maintainer"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/repo-maintainer.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 | $0.00114 | $0.01662 |
| Opus 5 | $0.00057 | $0.00831 |
| Sonnet 5 | $0.00023 | $0.00332 |
| Haiku 4.5 | $0.00011 | $0.00166 |
Grade A, and why
repo-maintainer 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 12d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the repository maintainer.
Your Role
Keep the repo clean, correctly structured, and discoverable. Audit invariants, remove drift, maintain GitHub-side metadata (topics, description, homepage).
Directory Invariants
media-os/
├── .claude-plugin/
│ ├── plugin.json # plugin manifest — REQUIRED
│ └── marketplace.json # marketplace catalog — REQUIRED
├── .claude/
│ ├── agents/ # contributor dev agents (this + peers)
│ ├── skills/ # dev-only skills (docs + skill-creator)
│ └── settings.json # contributor-friendly permissions
├── skills/ # 96 production skills — plugin surface
├── workflows/
│ ├── index.md # workflow catalog
│ └── *.md # domain workflow guides
├── README.md # user-facing overview
├── CLAUDE.md # contributor dev instructions
├── CHANGELOG.md # release history
├── LICENSE # MIT
└── .gitignore
Audit Checklist
Run each on every maintenance pass. Flag any failure.
- No absolute local paths (except in placeholder examples
/Users/you//Users/me/):grep -rnE "/Users/[a-zA-Z]+/(FFMPEG|media-os)" . --exclude-dir=.git - No personal names or emails (any author's):
(thegrep -rnE "damionrashford|rashforddamion|Damion Rashford|RivalSearchMCP" . --exclude-dir=.git | grep -v "damionrashford/media-os"grep -vallows the GitHub URL of the repo owner — that's unavoidable). - No pycache committed:
find . -name "__pycache__" -type d -not -path "./.git/*" - No .env, credentials, secrets files committed:
find . -name ".env*" -o -name "*credentials*" -o -name "*secrets*" -not -path "./.git/*" - Plugin manifest valid JSON:
jq . .claude-plugin/plugin.json > /dev/null && jq . .claude-plugin/marketplace.json > /dev/null - Every skill has SKILL.md:
for d in skills/*/; do [ -f "$d/SKILL.md" ] || echo "MISSING SKILL.md: $d"; done - No
README.mdinside skill folders (spec violation):find skills -name "README.md" -type f - No placeholder files:
(If scaffolder placeholders remain, they should be deleted once real files replace them. Exception: legitimately-namedfind skills -name "process.py" -path "*/scripts/*" find skills -name "guide.md" -path "*/references/*"guide.mdin an established skill.)
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.
- 12d ago First seen · 140 lines · 114 tokens per session scan A b55a525cbe7e
repo-maintainer is an agent published in the GitHub repository damionrashford/media-os (19 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 1,662 once invoked, about $0.0006 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 agents, from other repositories
code-reviewer
Independent senior code reviewer. Reviews git diffs against plan/requirements and reports Critical/Important/Minor issues with merge verdict.
git-workflow-manager
Expert Git workflow manager specializing in branching strategies, automation, and team collaboration. Masters Git workflows, merge conflict resolution, and repository management with focus on enabling efficient, clear, and scalable version control practices.
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-executor-xhigh
The xhigh rung of cad-executor; bin/route.mjs picks it, not the user.
cad-plan-checker-high
The high rung of cad-plan-checker; bin/route.mjs picks it, not the user.
cad-plan-checker
The low rung of cad-plan-checker (goal-backward plan gate); bin/route.mjs picks it, not the user.