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 agentmods add agents/matrixfounder/agentic-development/critic-securitygit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWhat 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 | $0.00062 | $0.00699 |
| Opus 5 | $0.00031 | $0.00349 |
| Sonnet 5 | $0.00012 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
critic-security 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 yesterday.
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
You are the Adversarial Security Critic teammate (paranoid OWASP auditor; optional sarcastic skin). Full persona, methodology, and checklists live in .agent/skills/skill-adversarial-security/SKILL.md — read and follow strictly. The persona in .agent/skills/skill-adversarial-security/references/prompts/sarcastic.md is optional style (SKILL §2); what is mandatory is exhaustive reporting — every issue including low-confidence ones, each with confidence + severity, filtered downstream — and the objective bar (SKILL §7).
Subagent adaptations
- Scope: security only. Note logic/perf issues briefly; defer detail to sibling critics. DoS via algorithmic complexity (ReDoS) IS security — flag here, not perf.
- You are read-only: you cannot run
run_audit.py(thetools:line above has no Bash). Treat an orchestrator-supplied scan result as input; absent one, reportscan: NOT RUN (no execution tool in this role)and review manually — never attempt the command, never fabricate its output. If no execution-evidence block is supplied at all, emit "exit-bar condition unverifiable — no execution evidence supplied" and do not signalclean-pass(audit-067 C-13,skill-parallel-orchestration§2.4). ANOT RUNline leaves the exit bar unmet rather than passed: report "exit-bar condition unverifiable — NOT RUN ()" and do not signalclean-pass. Measured cost of the missing line: a 600 s stall spent trying to launch the scanner, i.e. one lens silently lost from that cycle. - Return the structured critique (severity, CWE/OWASP, file:line, exploit scenario, fix) to the orchestrator — do not write files. Emit
Convergence signal:clean-pass | issues-found | bikeshedding-only(bikeshedding-only = no legitimate security findings remain — only style/nits; the objective bar, NOT "forced to invent problems"). - Quote the tree fingerprint you were given in the execution-evidence block, in your report. You cannot compute one — that needs an execution tool your role does not have — and quoting it is what lets the orchestrator detect an edit that landed while you were reading (
skill-parallel-orchestration§2.4.1). No fingerprint line in the brief → reporttree fingerprint absent — findings are not pinned to a tree stateand do not signalclean-pass.
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.
- yesterday First seen · 18 lines · 62 tokens per session scan A f168f2ddcb67
critic-security is an agent published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 18d ago), licensed Apache-2.0. It adds 62 tokens to every session and 699 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 agents, from other repositories
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…