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 V-Songbird/foundry --skill coordinate-readmesgit clone --depth 1 https://github.com/V-Songbird/foundryWrote 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/v-songbird/foundry/coordinate-readmes)<a href="https://agentmods.dev/skills/v-songbird/foundry/coordinate-readmes"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/coordinate-readmes/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/v-songbird/foundry/coordinate-readmes"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/coordinate-readmes.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 | $0.00048 | $0.00750 |
| Opus 5 | $0.00024 | $0.00375 |
| Sonnet 5 | $0.00010 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
coordinate-readmes 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 today.
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.
What it actually says
Coordinate plugin READMEs
This skill coordinates Claude/Codex edition pages and their shared main overview. Main retains the shared product story, branding, animation, benefits, mechanism, usage examples and general limitations, with a clear edition choice. Keep native install commands, compatibility details and measured tables in their editions. Use scripts/build-main-readmes.js to regenerate common content and validate main with check-main-frontpage.js --claude-ref Claude --codex-ref Codex. Common edition changes also update main before release. Flint is excluded from this main policy.
Locate both platform checkouts before editing. Use git worktree list or inspect
the other branch read-only; preserve uncommitted work and stay off main.
This is a Foundry development skill, not a skill shipped inside each plugin.
Use the same product narrative, headings, section order, common outcomes and
decorative branding in both editions. Read the current Foundry README template
and readme-parity rule. Preserve only the six named exception blocks:
identity, install, commands, compatibility, benchmarks, links.
Each difference needs a real platform or edition reason. Do not hide a rewrite
of the shared product story inside an exception or remove a supported feature
just because the other edition lacks it; identify that availability difference.
Use the same questions and table columns for benchmarks. Check original evidence
for the actual host, model, comparison, source date and metric. Keep limitations
and negative results. A benchmark's source date is distinct from the day someone
reviewed it. Never relabel another host's measurements or turn functional tests
into performance claims. Keep the table and mark missing values Not measured.
Paid runs and installs need their own authorization; an evidence gap is not it.
Run Foundry's scripts/git-hooks/check-readme-parity.js --pair <Claude-README> <Codex-README> and the README navigation check. For a committed pair, use
--git-pair <plugin-repo> <Claude-ref> <Codex-ref>. Each plugin also carries the
single-edition checker. Review benchmark sources independently of the parser;
passing a structural check does not establish experimental validity.
Report the common change, the justified exceptions, the exact pair checked and
any missing evidence. Carry shared edits to both working copies. Do not commit,
push or change repository protection settings unless that action is authorized.
For coordinated PRs, follow Foundry's .github/README_COORDINATION.md (also
present in each edition). Declare the opposite PR number and full head SHA in
both descriptions; rerun both checks after any head change. Candidate-pair
success is separate from the final integrated-branch comparison. Do not publish
selectors or pins until the integrated pair passes.
Apply the approved Ember art direction in docs/shared/launch/tinta-y-oficio.md. Match the name pill and decorative README accents to Hush blue, Foreman green and Razor red in both themes; preserve semantic data colors, original text and benchmark evidence.
Use the approved C layout in .github/PLUGIN_README_TEMPLATE.md: example-led introduction with mascot, benefits, mechanism, practical usage, installation, limits, evidence, references and license. Do not duplicate the promise in a TL;DR. Put measured graphics with evidence. Main keeps the shared story and offers an edition choice.
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.
- today First seen · 53 lines · 48 tokens per session scan A dc896a061514
coordinate-readmes is a skill published in the GitHub repository V-Songbird/foundry (4 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 750 once invoked, about $0.0002 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 2026-09-10.
Other skills, from other repositories
refactoring
Use when restructuring code without changing behavior -- extracting functions, renaming, moving files, reducing duplication, migrating between patterns (JS to TS, CJS to ESM), or addressing code smells. Covers safe refactoring workflows for any language.
clean-code
Use when the user writes new Python, or asks for review, refactor, or cleanup of Python code, names, comments/docstrings, functions, or tests. Applies Robert Martin's complete Clean Code catalog -- naming, functions, comments, DRY, boundary conditions, and tests -- to the code being changed.
oss-contrib
Use when contributing to open source projects from forked repositories. Handles upstream sync, CONTRIBUTING.md compliance, code style matching, PR preparation, and project-specific patterns. Activates for fork management, PR template filling, and upstream workflow compliance.
dev-workflow
Use when performing common development tasks like committing code, reviewing changes, running tests, fixing bugs, creating PRs, or checking repo status. Provides structured workflows for everyday git and development operations.
diff-explain
Use when you want a one-paragraph plain-English summary of what a diff does. Activates on "summarize this diff", "what does this PR do", "explain this branch", or when pointed at a PR URL or local branch.
phpunit-test-team-reviewing
Use this skill when the user asks for a team-based, consensus, multi-reviewer, or red-team review of Shopware PHPUnit tests — trigger phrases like "team review these tests", "consensus review the tests in PR.