Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/huuanh20/awesome-ai-agent-skillsnpx agentmods add skills/huuanh20/awesome-ai-agent-skills/sr-validateWrote 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/huuanh20/awesome-ai-agent-skills/sr-validate)<a href="https://agentmods.dev/skills/huuanh20/awesome-ai-agent-skills/sr-validate"><img src="https://agentmods.dev/badge/skills/huuanh20/awesome-ai-agent-skills/sr-validate/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/huuanh20/awesome-ai-agent-skills/sr-validate"><img src="https://agentmods.dev/badge/skills/huuanh20/awesome-ai-agent-skills/sr-validate.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 | $0.00059 | $0.00583 |
| Opus 5 | $0.00030 | $0.00292 |
| Sonnet 5 | $0.00012 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
sr:validate 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.
What it actually says
sr:validate
Goal: validate the generated SRS against IEEE 830-1998. Fix all ERRORs before reporting. WARNings are captured for the improvement report.
Step 0 — Identify Project
AskUserQuestion: "Which project to validate? (slug)"
Check that projects/{slug}/srs/ exists and contains .md files.
If missing: tell user to run /sr:generate first.
Step 1 — Run Validator
Execute:
python .claude/scripts/srs_validator.py --dir projects/{slug}/srs/
Capture stdout. Display the full validation table.
Step 2 — Fix ERRORs Immediately
For each ERROR finding:
- Identify the affected SRS section file
- Fix the issue following IEEE 830 rules:
missing-section: add the section with correct heading formatfr-no-shall: rewrite the Requirement line with explicit "shall" clausefr-numbering-gap: renumber FRs to fill gaps (update all references)
- State what was fixed:
FIXED [ERROR] fr-no-shall in FR-07 → added "shall" clause
After fixing all ERRORs: re-run validator and confirm no new ERRORs.
Step 3 — Collect WARNings
List all WARN findings but do NOT fix them here — they go into the improvement report.
Format:
WARN: unresolved-tag — 3 [TBD] tags remain (NFR-03, NFR-07, §1.3)
WARN: fr-incomplete-gwt — FR-12: missing "Then:" field
WARN: nfr-no-numeric — NFR-05 Response Measure has no numeric threshold
Step 4 — Verdict
Output:
## Validation Result
Verdict: COMPLIANT | PARTIALLY COMPLIANT | NON-COMPLIANT
File: projects/{slug}/srs/ ({N} files)
ERRORs fixed: {count}
WARNings open: {count} → captured in /sr:improve report
Next: /sr:improve → improvement report + warning resolution guide
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 · 84 lines · 59 tokens per session scan A ee0600f339f1
sr:validate is a skill published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 583 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
obsidian
Read, search, and create Markdown notes inside an Obsidian vault on disk.
Manipulate PDF files — merge, split, extract pages/text, PDF↔images, OCR, info — via the qpdf / poppler / ocrmypdf CLIs. Use to combine, slice, convert, or OCR PDFs.
pandoc
Convert documents between formats (Markdown, DOCX, HTML, PDF, RST, EPUB, LaTeX) via the pandoc CLI. Use to transform a document from one format to another.
xlsx
Create and edit Excel .xlsx workbooks (sheets, cells, formulas, formatting) via Python openpyxl. Use to generate spreadsheets or write/update cells. Reading is via os.fs.readdocument.
material-organizer
Organize user-provided materials or local folders into traceable notes, knowledge cards, categories, indexes, and cleanup plans. Use this skill whenever the user asks to organize multiple links, files, snippets, research materials, downloads, personal knowledge flow materials, or a local directory.
math-tutor
Do not use for open-ended mathematical modeling, Python/local expression calculation, Wolfram-style symbolic computation, university-level research math, or generic homework tutoring outside math. Do not promise PDF export, external account sync, persistent error-book storage, or regional textbook coverage unless the…