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 rjmurillo/ai-agents --skill spec-generatorgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/spec-generator)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/spec-generator"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/spec-generator/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/rjmurillo/ai-agents/spec-generator"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/spec-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 221 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.
- medium Agent Snooping · line 17 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00099 | $0.03244 |
| Opus 5.5 | $0.00040 | $0.01298 |
| Sonnet 5.5 | $0.00020 | $0.00649 |
| Haiku 4.5 | $0.00010 | $0.00324 |
Grade A, and why
spec-generator 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 22d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Generator Skill
Transform feature descriptions into 3-tier specifications: Requirements (WHAT/WHY) then Design (HOW) then Tasks (IMPLEMENTATION). Produce when context is sufficient. Push back when it is not.
This skill supersedes the former spec-generator agent. The change exists because the agent emitted invalid frontmatter enum values on every spec PR (PR #1995 drew 9 schema-violation threads; PR #1989 the same) because it wrote frontmatter from memory instead of reading the schema. This skill bundles the schema and a deterministic validator so the drift cannot ship.
Prose Self-Check
Before emitting any prose artifact (spec narrative, requirements, design, tasks, PR or issue body), run the prose-self-check skill (.claude/skills/prose-self-check/SKILL.md): four-layer AI-vernacular audit; weight structural and semantic findings above lexical; do not flag low-signal words on presence alone.
Triggers
| Phrase | Action |
|---|---|
/spec Step 6 (formalize PRD) |
Generate REQ/DESIGN/TASK artifacts |
generate spec, formalize requirements |
Natural-language activation |
create requirements/design/tasks |
Alternative trigger |
BLOCKING: Schema Compliance (read before writing any spec file)
The frontmatter schema is bundled at references/spec-schemas.md; .agents/governance/spec-schemas.md is the canonical source for frontmatter fields. The body-section checklist in the bundled reference documents this skill's ontology contract; validate_spec_frontmatter.py validates frontmatter only, while structural tests and the CI completeness prompt enforce ontology body sections. You MUST:
-
Read
references/spec-schemas.mdbefore emitting any frontmatter. -
Use only these enum values. They are copied verbatim from the schema:
Field Type Allowed values typeall requirement,design,taskstatusrequirement, design draft,review,approved,implemented,rejectedstatustask todo,in-progress,blocked,done,cancelledpriorityall P0,P1,P2categoryrequirement functional,non-functional,constraintcomplexitytask XS,S,M,L,XL
What ships with it
4 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.
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.
- 22d ago Changed · +5 lines eaf680e43f78
- 24d ago Changed da4f031e2da7
- 25d ago Changed · +14 lines 645bd9942b7c
- 1mo ago Changed · +29 tokens per session 00d8564f6f17
- 1mo ago First seen · 222 lines · 70 tokens per session scan A 08f84b382679
spec-generator is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 3,244 once invoked, about $0.0004 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
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.