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 ymm-oss/fsl --skill fsl-requirements-documentgit clone --depth 1 https://github.com/ymm-oss/fslWrote 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/ymm-oss/fsl/fsl-requirements-document)<a href="https://agentmods.dev/skills/ymm-oss/fsl/fsl-requirements-document"><img src="https://agentmods.dev/badge/skills/ymm-oss/fsl/fsl-requirements-document/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/ymm-oss/fsl/fsl-requirements-document"><img src="https://agentmods.dev/badge/skills/ymm-oss/fsl/fsl-requirements-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Prompt Injection · line 56 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00145 | $0.02359 |
| Opus 5.5 | $0.00058 | $0.00944 |
| Sonnet 5.5 | $0.00029 | $0.00472 |
| Haiku 4.5 | $0.00015 | $0.00236 |
Grade A, and why
fsl-requirements-document 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FSL Requirements Document — Generate, Annotate, Re-check
This skill turns a checked requirements (or direct spec) dialect file into a
requirements document stakeholders can read, using the Requirement Claim IR (RCIR)
pipeline: fslc document claims (the machine-readable contract), fslc document generate (deterministic ja/en Markdown), and fslc document check (structural
drift detection). See ../fsl/SKILL.md and use its reference index only as needed
for FSL syntax, verification, and repair — this skill only covers the
document layer built on top of an already-checked spec. If the .fsl itself still
needs authoring or repair, use fsl-requirements (or fsl-design) first and come
back here once fslc check/fslc verify are green.
What this skill is for
The agent is an editor of non-normative content and a review-support
assistant, not a compiler. Every normative sentence in the document — enablement
conditions, effects, postconditions, fairness, deadlines, acceptance/forbidden
traces — comes from a fixed template deterministically rendered from the checked
FSL (issue #326). The agent never writes that text; it only fills in the one
editable slot the generator leaves open (background), and only ever proposes
findings about the source material, never encodes them into the normative
sections itself.
Permitted operations
- Edit the non-normative
backgroundslot: project context, a plain-language summary, review notes for stakeholders. - Propose a chapter reordering based on RCIR's own structure (e.g. grouping requirements by theme) — a suggestion for a human to apply, not a rewrite of generated content.
- Draft glossary candidates (issue #330) for terms that appear in requirement text or claims.
- Flag a candidate mismatch between the original requirement text and the formalized meaning as an advisory note — for example, source text that says "exactly once" where the formalized guard only enforces "at most once." Never strengthen the FSL-derived meaning to match the source text to make the mismatch disappear. Surfacing the gap is the value; resolving it is a human decision.
- Flag a missing requirement tag, a missing
acceptance/forbiddencase, or anundecideditem that looks resolvable, as a review note. - Point a stakeholder at a requirement whose assurance class is
not_runin every dimension (issue #332) as a review note — never supply evidence yourself or assert a stronger class than the document already shows; the--evidencefiles come from real verification runs, not from the agent. - Point a stakeholder at a document with no "Approval records" section (issue #333) as a review note ("this document is not yet approved") — never fabricate an approval record or assert that a document is approved without one.
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.
- 1mo ago First seen · 167 lines · 145 tokens per session scan A 04f032ac1810
fsl-requirements-document is a skill published in the GitHub repository ymm-oss/fsl (34 stars, last pushed today), licensed Apache-2.0. It adds 145 tokens to every session and 2,359 once invoked, about $0.0006 per session on Opus 5.5. 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 skills, from other repositories
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
docetl
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
review-export
Export CocoReview reports as markdown, html, or pdf-ready status artifacts. Usage: $review export markdown|html|pdf [report-path].
data-science-analysis
Computes a numeric or categorical answer to a quantitative data-science question by cleaning and analyzing local data files (CSV, Excel, TSV, and scientific formats .npz/.fits/.h5) with pandas, numpy, and scipy. Use whenever a task ships its own dataset (in whatever local directory it provides) and asks you to derive…
docutranslate
Use when translating PDF/Word/Excel/Markdown/EPUB/SRT documents locally with an LLM while keeping layout — docutranslate -i on port 8010, docutranslate.sdk Client(translate/save), docutranslate --mcp for stdio/SSE MCP, MinerU token for PDF parsing; also for missing DOCUTRANSLATEAPIKEY, PDF layout loss after md…
python-style
Validate Python code against style and architectural conventions.