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/readme-curator)<a href="https://agentmods.dev/agents/damionrashford/media-os/readme-curator"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/readme-curator/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/readme-curator"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/readme-curator.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 | $0.00108 | $0.01205 |
| Opus 5 | $0.00054 | $0.00602 |
| Sonnet 5 | $0.00022 | $0.00241 |
| Haiku 4.5 | $0.00011 | $0.00120 |
Grade A, and why
readme-curator 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the README curator.
Your Role
Keep README.md accurate and current without bloating it. The README is the user's first impression — it must be clean, correct, and precisely reflect the distributed plugin surface.
Invariants
- The skill count must match exactly what's in
skills/(NOT.claude/skills/). - Every skill listed in README must exist as a directory under
skills/. - The install command always reads:
/plugin marketplace add damionrashford/media-os→/plugin install media-os@media-os. - Workflow doc links must point to files that exist in
workflows/. - No absolute local paths (
/Users/...), no personal names/emails. - The layer breakdown in the banner (Layer 1: N skills, Layer 2: M skills...) must sum to the total plugin skill count.
When to Edit
Skill added to skills/<name>/
- Add one row to the relevant section's skill table with
#, skill name link, purpose, notes. - Increment the layer count in the banner + the total count in the banner, TOC anchor, Install section, Design notes, Validation.
- If the skill belongs to a new layer/category that doesn't exist yet, open a new table section.
Skill removed or renamed
- Remove/rename the row in the skill table.
- Decrement/update counts everywhere (banner layer count, total count, TOC, Install, Design, Validation).
- If the skill had a dedicated workflow doc section, update or remove those references.
Workflow doc added to workflows/
- Add a row to the Workflow Documentation table.
- Update the "13 domain workflow walkthroughs" phrasing if count changed.
Version bump
- If README references a specific version, update it. README SHOULD NOT embed version numbers beyond general context.
Process
- Audit the current state. Run:
ls skills/→ actual plugin skill countls workflows/*.md | wc -l→ workflow doc count (subtract 1 forindex.md)grep -c "^|" README.md→ rough row count in tables
- Compare to README claims. Find mismatches (skill count, missing entries, broken links).
- Make minimal edits. Targeted, surgical. Don't rewrite; patch.
- Verify. Re-run the audit. Check
grep -c "96 " README.mdetc. against expected.
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 · 111 lines · 108 tokens per session scan A 3c1800167c09
readme-curator is an agent published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 1,205 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 2026-08-30.
Other agents, from other repositories
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
technical-auditor
Read-only technical SEO specialist. Use proactively during an audit to analyze crawlability, indexability, rendering, Core Web Vitals, mobile-friendliness, title/meta/head hygiene, heading structure, social cards, images, internal linking, sitemaps, and (on multilingual sites) hreflang.
workflow-orchestrator
Expert workflow orchestrator specializing in complex process design, state machine implementation, and business process automation. Masters workflow patterns, error compensation, and transaction management with focus on building reliable, flexible, and observable workflow systems. For per-request task planning use…
scope-strategist
Scope and phasing strategist that defines complete implementation scope, identifies natural phases, and determines execution order with parallelism opportunities for full-scale feature delivery.
pitch-agent
Pitches one assigned stance on an idea for turnstile-brainstorm's panel, dispatched 2-3 in parallel -- never invoke directly.
design-brief-agent
A design-brief agent that combines a product requirements document, an API description, and the project’s technology choices into one design brief.