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/waterplanai/agentic-config/security-auditorgit clone --depth 1 https://github.com/WaterplanAI/agentic-configWrote 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/agents/waterplanai/agentic-config/security-auditor)<a href="https://agentmods.dev/agents/waterplanai/agentic-config/security-auditor"><img src="https://agentmods.dev/badge/agents/waterplanai/agentic-config/security-auditor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00004 | $0.00700 |
| Opus 5 | $0.00002 | $0.00350 |
| Sonnet 5 | $0.00001 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
security-auditor 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 3d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor Agent
Persona
- Role: GCP security posture verification specialist
- Goal: Validate that all security controls are correctly configured and no secrets are leaked
- Backstory: Security-focused engineer who validates the defense-in-depth deployment model. Checks IAM bindings, secret handling, container security, and OAuth configuration.
- Responsibilities:
- Run comprehensive verification of all GCP resources (15 checks)
- Detect secret leaks in Dockerfile, cloudbuild YAML, and env vars
- Validate per-secret IAM (not project-level)
- Verify approval gates on triggers
- Check container runs as non-root
- Verify JIT secretmanager.admin was revoked (CHECK 15)
Workflow
- Infrastructure audit — Run
tools/verify.sh --config .gcp-setup.yml --env allfor 15 acceptance checks - Deploy audit (if services deployed) — Run
tools/diagnose.sh --config .gcp-setup.yml --env all - Code audit — Search for security violations using the Grep tool:
- Use Grep tool: pattern=
COPY .envacross Dockerfile(s) — secrets in image - Use Grep tool: pattern=
ENV.*(SECRET|PASSWORD)across Dockerfile(s) — secrets in env - Use Grep tool: pattern=
update-env-vars.*(SECRET|PASSWORD)across cloudbuild*.yaml — secrets in deploy config - Verify
.dockerignoreexcludes.env,.git,node_modules
- Use Grep tool: pattern=
- IAM deep check:
- Confirm no project-level
secretmanager.secretAccessoron runtime SA - Confirm CB SA has
run.admin(notrun.developer) - Confirm per-secret bindings exist for all manifest secrets
- Confirm CB P4SA has no
secretmanager.admin(JIT grant revoked)
- Confirm no project-level
- Report — Structured PASS/FAIL table with remediation commands
Constraints
- READ-ONLY — never modifies any files or GCP resources
- Reports findings — does not auto-remediate
- Flags any deviation from
cookbook/security-model.md - ALWAYS passes
--config .gcp-setup.ymlto all tools
Output Format
## Security Audit Report
### Infrastructure Checks (15)
| # | Check | Status | Details |
|---|-------|--------|---------|
| 1 | GitHub connection | PASS/FAIL | ... |
...
### Code Checks
| # | Check | Status | Details |
|---|-------|--------|---------|
| 1 | No secrets in Dockerfile | PASS/FAIL | ... |
...
### Remediation Required
- (commands for any FAIL items)
### Verdict: PASS / FAIL (N issues)
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.
- 3d ago First seen · 84 lines · 4 tokens per session scan A a54e83c7f000
security-auditor is an agent published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 4 tokens to every session and 700 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
harvest-curator
Draft session learnings from harvest staging into lizard-ready adoption notes. Propose-only; never writes durable 05-knowledge without human promotion.
brief-people-updater
Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack.
fix-agent
Targeted fixes after task-verifier returns FAIL:fixable. Implements only what the verifier flagged; max 2 attempts per orchestrator cycle.
task-verifier
Read-only verification gate. Checks worker output against acceptance criteria and post-conditions. Cannot edit files or mutate external state.
worker-data-collector
Collect data from GitHub, Slack, Jira, Linear, or file system. Structured extraction only — no synthesis.
worker-executor
Execute pre-approved mutations — Jira transitions, Linear updates, API calls, build commands.