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 ai-agents-architecture-contractgit 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/ai-agents-architecture-contract)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/ai-agents-architecture-contract"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-architecture-contract/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/ai-agents-architecture-contract"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-architecture-contract.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 Anti-Refusal · line 44 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00111 | $0.05963 |
| Opus 5.5 | $0.00044 | $0.02385 |
| Sonnet 5.5 | $0.00022 | $0.01193 |
| Haiku 4.5 | $0.00011 | $0.00596 |
Grade A, and why
ai-agents-architecture-contract 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 4d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agents Architecture Contract
This skill is the map of design decisions that hold this repository up: what is canonical, what is generated, which invariants are enforced by gates, and where the structure is honestly weak. Read it before any change that touches more than one tree, any hook, any plugin surface, or any generated file. The repo's governance runs on observable evidence, not trust: active requirements name evidence that exists independent of any committed session log, so almost every claim below is backed by a gate you can run. (PR #5135, 2026-08-18, retired the earlier "verification-based enforcement" wording in favor of this evidence-sink framing; SESSION-PROTOCOL.md, the doc that carried that wording, was later deleted along with the session skill cluster.)
Triggers
which tree is canonicalarchitecture contractwhy is this designed this waywhat invariant am I about to breakwhere is the source of truth for this file
Process
Phase 1: Locate the source of truth before touching any file
The generation seam is ASYMMETRIC. There is no single "templates in, everything out" pipeline. Two seams coexist (ADR-072, status Proposed, corrected this premise explicitly: "the seam is asymmetric"):
- Agents: ADR-109 B1 made
templates/agents/canonical for every agent tree.<stem>.claude.md.tmplrenderssrc/claude/agents/<stem>.md,<stem>.copilot.md.tmplrenderssrc/copilot-cli/agents/<stem>.mdand.github/agents/, and<stem>.shared.mdrenderssrc/vs-code-agents/and feedsdocs/agent-catalog.md..claude/agents/is a binplace copy ofsrc/claude/agents/(see the table row below). - Rules, skills, hooks: ADR-109 B2 to B4 made
templates/rules/,templates/skills/, andtemplates/hooks/canonical for the Claude tree.rule_templates.py,skill_templates.py, andhook_templates.pyrender intosrc/claude/, and the binplace step copies the result into.claude/. A skill's other files (references, scripts) stay hand-maintained under.claude/skills/<name>/. Generators emit other harnesses' mirrors. There is no commands class: ADR-064 (issue #5632) converted every command into a skill and deleted the commands-to-skills bridge, so skills are the single user-invocable surface andcheck_commands_retired.pyblocks a command coming back.
What ships with it
3 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.
- 4d ago Changed 620193562e76
- 5d ago Changed · +2 lines 2e7303a6dfa8
- 6d ago Changed · +1 lines 36930597da5e
- 16d ago Changed b8d9f8131867
- 22d ago Changed · +6 lines 0f1da71854a2
- 1mo ago Changed · +2 lines 67f85a8223c3
- 1mo ago Changed 112e9e13bfc7
- 1mo ago Changed · -1 lines 19e86a59ba54
- 1mo ago Changed 26285dd3a52d
- 1mo ago First seen · 174 lines · 111 tokens per session scan A 81d3e63637b7
ai-agents-architecture-contract is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 5,963 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.