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 simota/agent-skills --skill scribegit clone --depth 1 https://github.com/simota/agent-skillsWrote 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/simota/agent-skills/scribe)<a href="https://agentmods.dev/skills/simota/agent-skills/scribe"><img src="https://agentmods.dev/badge/skills/simota/agent-skills/scribe/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/simota/agent-skills/scribe"><img src="https://agentmods.dev/badge/skills/simota/agent-skills/scribe.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 6 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 | $0.00052 | $0.05652 |
| Opus 5.5 | $0.00021 | $0.02261 |
| Sonnet 5.5 | $0.00010 | $0.01130 |
| Haiku 4.5 | $0.00005 | $0.00565 |
Grade A, and why
scribe 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 7d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scribe
Authoritative specification writer for standalone formal documents and cross-team unified packages. Convert evidence, ideas, and decisions into one traceable, implementation-ready source of truth. Do not write code or make architecture decisions.
What ships with it
34 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _common 10 B
- reference/adr-writing.md 7.5 KB
- reference/anti-patterns.md 7.7 KB
- reference/api-documentation.md 10 KB
- reference/autorun-schema.md 1023 B
- reference/checklist-template.md 3.1 KB
- reference/design-template.md 4.3 KB
- reference/document-types.md 2.4 KB
- reference/documentation-calibration.md 6.1 KB
- reference/format-conversion/conversion-matrix.md 4.5 KB
- reference/format-conversion/format-conversion-anti-patterns.md 2.6 KB
- reference/mend 10 B
- reference/prd-template.md 7.7 KB
- reference/recipes-index.md 3.8 KB
- reference/reference-index.md 3.6 KB
- reference/runbook-writing.md 5.9 KB
- reference/srs-template.md 4.5 KB
- reference/test-spec-template.md 3.0 KB
- reference/unified-spec/bdd-best-practices.md 3.8 KB
- reference/unified-spec/business-tech-translation.md 2.8 KB
- reference/unified-spec/cross-reference-guide.md 3.0 KB
- reference/unified-spec/handoff-formats.md 5.0 KB
- reference/unified-spec/interaction-triggers.md 5.0 KB
- reference/unified-spec/raci-matrix.md 8.6 KB
- reference/unified-spec/README.md 1.6 KB
- reference/unified-spec/scope-modes.md 610 B
- reference/unified-spec/specification-anti-patterns.md 2.7 KB
- reference/unified-spec/specification-calibration.md 3.9 KB
- reference/unified-spec/stakeholder-map.md 8.0 KB
- reference/unified-spec/template-selection.md 2.1 KB
- reference/unified-spec/traceability-pitfalls.md 2.9 KB
- reference/unified-spec/unified-template.md 7.7 KB
- reference/unified-spec/user-story-mapping.md 9.1 KB
- reference/unified-spec/user-story-smells.md 2.5 KB
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.
- 7d ago Changed · +1 lines 7f8d05416cd7
- 12d ago Changed 10c9614d658e
- 14d ago Changed dff036f1312f
- 17d ago Changed 98373a6c5bff
- 1mo ago Changed · -1 lines 4979bba1d2fa
- 1mo ago First seen · 358 lines · 52 tokens per session scan A 8f642aa7f1fe
scribe is a skill published in the GitHub repository simota/agent-skills (95 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 5,652 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
deep-review
Parallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency, error-handling, frontend, testing), each with a focused checklist and isolated context. Synthesizes findings into unified report with FIX/DEFER/ACCEPT triage. Use…
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
hook-regenerate
Rebuild AIWG hook files from currently installed framework manifests.