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 analyzegit 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/analyze)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/analyze"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/analyze/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/analyze"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.01587 |
| Opus 5 | $0.00053 | $0.00794 |
| Sonnet 5 | $0.00021 | $0.00317 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
analyze 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 8d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Skill
When this skill activates, IMMEDIATELY invoke the script. The script IS the workflow. Do NOT explore the codebase first.
Triggers
analyze this codebase- architecture and quality focusreview code quality- quality focusrun security assessment- security focusarchitecture review of this system- architecture focusfind code smells- quality focus
Quick Reference
| Input | Focus | Minimum Steps |
|---|---|---|
| Architecture review | Structure, dependencies, layering | 6 |
| Security assessment | Input validation, auth, data handling | 7-9 |
| Code quality | Duplication, complexity, test gaps | 6-7 |
| Broad investigation | All dimensions | 9-12 |
Security
When using the Bash tool, all arguments containing variable or user-provided input MUST be quoted to prevent command injection vulnerabilities. Refer to the repository style guide on Command Injection Prevention (CWE-78).
WRONG: grep $PATTERN /some/path
CORRECT: grep -- "$PATTERN" /some/path
When to Use
Use this skill when:
- Investigation spans multiple files or components
- Analysis requires structured multi-step exploration
- Findings need prioritization by severity with file:line evidence
Use direct code reading instead when:
- Checking a single file or function
- The question has a known, specific location
- A quick grep or symbol search answers the question
References
- Working with Legacy Code - Bottom-up refactoring through the Software Hierarchy of Needs
- OODA Loop - Decision-making framework mapped to analyze phases
- Tell, Don't Ask - Detect feature envy and getter chain code smells
- Boy Scout Rule - Scope improvement recommendations by size
- Observability Pillars - Logs, metrics, traces for investigation methodology
- Engineering Complexity Tiers - Classify components by tier, evaluate pattern appropriateness
- Agent Architecture Patterns - Skill budget rule, structured prompt design, diagnostic signals for agent reliability
- Context Budget Management - Context flood prevention, Think in Code principle, hook architecture for session continuity
What ships with it
10 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.
- references/agent-architecture-patterns.md 2.2 KB
- references/context-budget-management.md 1.7 KB
- references/design-legacy-code.md 2.3 KB
- references/design-tell-dont-ask.md 2.2 KB
- references/DEVELOPMENT.md 2.4 KB
- references/engineering-complexity-tiers.md 5.0 KB
- references/quality-boy-scout-rule.md 1.9 KB
- references/reliability-observability-pillars.md 2.9 KB
- references/strategy-ooda-loop.md 2.3 KB
- scripts/analyze.py 26 KB runs code
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.
- 8d ago First seen · 172 lines · 107 tokens per session scan A a832f5ff2b62
analyze is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 1,587 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
ax-annotation
@AX code annotation workflow skill for agent-driven tag application.
semantic-slicing
Build local semantic review slices by combining clawpatch feature maps, deepsec threat candidates, visual review maps, and optional gitcrawl/discrawl evidence for repos such as openclaw/openclaw.
workspace-diff-review
Reviews the current workspace diff with a pre-landing mindset.
code-review-skill
Reviews code for bugs, inefficiencies, and adherence to best practices, providing actionable improvement suggestions.
robin
Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to…
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.