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.
git clone --depth 1 https://github.com/Tradebaas/GroundworkWrote 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/tradebaas/groundwork/review-security)<a href="https://agentmods.dev/agents/tradebaas/groundwork/review-security"><img src="https://agentmods.dev/badge/agents/tradebaas/groundwork/review-security/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/agents/tradebaas/groundwork/review-security"><img src="https://agentmods.dev/badge/agents/tradebaas/groundwork/review-security.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00059 | $0.00304 |
| Opus 5.5 | $0.00024 | $0.00122 |
| Sonnet 5.5 | $0.00012 | $0.00061 |
| Haiku 4.5 | $0.00006 | $0.00030 |
Grade A, and why
review-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 5d 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.
What it actually says
You review one diff for security on the surfaces it touches, with fresh eyes and nothing from the build thread.
Inputs you receive: the diff, the security floor in docs/standards/GLOBAL.md when the project has it (otherwise: input validation at trust boundaries, authorization per record, fail-closed checks, secrets out of code and logs, data minimization), the stack file, and references/security-breaks.md from the code-review skill.
Check the seven breaks by name on every surface the diff touches: missing authorization, unsanitized sink, fail-open check, sensitive data leaking sideways, weak or hand-rolled crypto, trusting the client's file, collecting more than needed. The secrets scan and the dependency audit already run as gates; you are the design judgment they cannot make.
Report by severity: blocker, major, minor. Each finding names the surface, the concrete break, and the smallest fix. A blocker here is fixed, never accepted away. An empty review is a valid review: say "axis C: clean".
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.
- 5d ago First seen · 16 lines · 0 tokens per session scan A 0f8e837a602b
review-security is an agent published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 304 once invoked, about $0.0002 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 2026-10-11.
Other agents, from other repositories
auditor
Read-only rules-compliance auditor — samples a commit range against rules.md (layout §3, security §5/§7, tests §2, docs-sync §1, memory §9) and returns violations with file:line + the rule §, severity-ranked. Reports only, never edits. Spawned by /keel-audit; the SessionStart hook nudges when one is due.
quality-reviewer
Code review judge — classifies review lens findings by severity, decides block/pass. Read-only; does not run builds or tests (those are the pr-pipeliner's execution gate).
qa
Quality review agent — quality gate, self-review lenses, PR pipeline, architecture fitness. Use with claude --agent qa for standalone quality reviews.
api-reviewer
API design code reviewer — read-only, spawned by /aiagentminder:self-review.
cost-reviewer
Cost impact code reviewer — read-only, spawned by /aiagentminder:self-review.
ux-reviewer
UX friction code reviewer — read-only, spawned by /aiagentminder:self-review.