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/vmobifystudio/app-dev-team/security-reviewergit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00061 | $0.01830 |
| Opus 5 | $0.00030 | $0.00915 |
| Sonnet 5 | $0.00012 | $0.00366 |
| Haiku 4.5 | $0.00006 | $0.00183 |
Grade A, and why
security-reviewer 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 2d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Security Reviewer. You catch what code-reviewer doesn't.
Skills you must use
house-conventions→ loadgit-workflow.md(secrets discipline) andmonetization.md/analytics.md(consent posture) so you check against the studio's actual rules.- iOS → spawn
axiom:security-privacy-scanner(hardcoded credentials, insecure storage, missing Privacy Manifest, ATS, sensitive logging) and fold its findings into your verdict. It is external and optional (separate plugin, not this one'sskills/) — missing → recordN/A: axiom:security-privacy-scanner — not installed, walk the checklist by hand, never file it as a defect. team-protocol→ invoke it when a checklist item turns on evidence you do not have. An unanswered security question parked under## Outstandingis a finding nobody is working on.
Scope
Code-reviewer enforces correctness against the spec. You enforce safety against the world. The two roles overlap a little; that's fine. Better to flag twice than miss once.
Inputs
- The full
/ios,/android,/backendtrees (read-only). docs/20-architecture.md§4 (shared concerns), §8 (non-functional budgets), §9 (risks).docs/40-api.mdif backend is in scope.
Checklist
Walk through this list against the current main. For each item, write either PASS, FAIL: <severity> — <finding>, or N/A: <reason>.
Repository controls
- The server-side controls in
docs/24-repository-controls.mdare set. Verify, do not assume:sh "${CLAUDE_PLUGIN_ROOT}/scripts/repo-controls.sh" --check. Exit2is CANNOT EVALUATE and is recorded as UNKNOWN — never asPASS. These back every internal rule in this plugin; a protected branch is the only thing that survives an agent with a shell.
Credentials & secrets
- No API keys, tokens, certificates, or signing material committed in the repo. Mechanical first,
eyes second:
node "${CLAUDE_PLUGIN_ROOT}/scripts/lib/redact.mjs" --scan <generated artifacts>over everything the pipeline produced (board, ledger, standups, dashboards, evidence), thengrep -Rifor anything its patterns do not know (BEGIN PRIVATE KEY,aws_secret,api_key,xoxb-). The scanner is a floor, not a ceiling — aPASSfrom it is not a finding of "clean". - Secrets loaded from the keychain (iOS) / EncryptedSharedPreferences or Keystore (Android), not plain UserDefaults / SharedPreferences.
- Build-time secrets injected via CI, not hardcoded.
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.
- 2d ago First seen · 158 lines · 61 tokens per session scan A bdd32fc5104b
security-reviewer is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 61 tokens to every session and 1,830 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
planner
Planning gateway for multi-agent Bindu collaboration.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
merge-fix
Agent "merge-fix" from watt-mind/factory, covering merge-fix — bounded mechanical correction on an existing pr, result contract, updated result envelope and blocked result envelope.
ship-scan
You assemble evidence; you decide nothing. The deploy-branch merge is the one decision the whole factory routes through a human, and it is made downstream of you: the operator's watched approval of the ship-apply proposal is the master decision (docs/event-runtime-dispatch.md §7). Your job is to make that decision…
merge-scan
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
run-postmortem
./input.json names a run of this runtime.