Borrowing it
Nothing to install: this file belongs to ambient-code/platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ambient-code/platform/main/.claude/agents/security-review.mdgit clone --depth 1 https://github.com/ambient-code/platformWrote 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/ambient-code/platform/security-review)<a href="https://agentmods.dev/agents/ambient-code/platform/security-review"><img src="https://agentmods.dev/badge/agents/ambient-code/platform/security-review/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/ambient-code/platform/security-review"><img src="https://agentmods.dev/badge/agents/ambient-code/platform/security-review.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 | $0.00039 | $0.01229 |
| Opus 5.5 | $0.00016 | $0.00492 |
| Sonnet 5.5 | $0.00008 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
security-review 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- security-review — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review Agent
Cross-cutting security review against documented security standards.
Context
Load these files before running checks:
specs/standards/security/security.spec.md
Checks
S1: User token for user operations (Blocker)
Handlers must use GetK8sClientsForRequest(c) for user-initiated operations. Service account only for privileged operations after RBAC validation.
# Find handler functions using service account clients without RBAC validation
rg -n "GetK8sClientsForRequest|serviceAccountClient|saClient" components/ --glob="*.go" | grep -v "_test.go"
# Flag handlers that don't call GetK8sClientsForRequest (manual review for user-flow endpoints)
rg -n "func.*Handler\|func.*Handle" components/backend/ --glob="*.go" -A 5 | grep -v "GetK8sClientsForRequest" | grep "func.*Handler"
S2: RBAC before resource access (Critical)
SelfSubjectAccessReview (or equivalent authz check) should precede user-scoped resource access.
# Find SelfSubjectAccessReview usage — flag user-resource endpoints that lack it
rg -n "SelfSubjectAccessReview|SubjectAccessReview" components/ --glob="*.go" | grep -v "_test.go"
# Find resource access patterns without preceding RBAC check (flag for manual review)
rg -n "client\.Get\|client\.List\|client\.Create" components/backend/ --glob="*.go" -B 10 | grep -v "SelfSubjectAccessReview"
S3: Token redaction in all outputs (Blocker)
No tokens in logs, errors, or API responses. Use len(token) for logging.
# Find token variables logged directly (should use len(token) instead)
rg -n "log.*[Tt]oken\|Sprintf.*[Tt]oken\|Error.*[Tt]oken" components/ --glob="*.go" | grep -v "_test.go" | grep -v "len(token)"
# Find token values in response bodies
rg -n '"token"\s*:\s*[a-zA-Z]' components/ --glob="*.go" | grep -v "_test.go"
S4: Input validation (Major)
DNS labels validated, URLs parsed, no raw newlines for log injection.
# Find URL construction without url.Parse validation
rg -n "url\.Parse\|url\.ParseRequestURI" components/ --glob="*.go" | grep -v "_test.go"
# Find log statements with user-controlled input (potential log injection via newlines)
rg -n 'log\.(Info|Error|Warn).*(name|label|input|param|query)' components/ --glob="*.go" | grep -v "_test.go"
# Find DNS label handling without regex validation
rg -n "IsDNSLabel\|dns1123\|ValidateName" components/ --glob="*.go" | grep -v "_test.go"
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.
- 1mo ago First seen · 129 lines · 39 tokens per session scan A c8804cea7434
security-review is an agent published in the GitHub repository ambient-code/platform (131 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,229 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 2026-08-30.
Other agents, from other repositories
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.
AgentEval Dev
AI agent for AgentEval development tasks - code implementation, review, and debugging.
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…
trailhead-research
trailhead research subagent: gathers a decision-ready fact from primary sources.
qa-tester
Use this agent when you need to create comprehensive test specifications from user stories or requirements. This includes analyzing user stories to extract testable scenarios, developing detailed test cases with clear steps and expected outcomes, and creating structured test specification files that follow testing…
consumer-app-pm-reviewer
PM-side reviewer for consumer-app archetype products. Stress-tests strategy / spec / launch plans against consumer-app patterns — retention curves, viral loops, UA economics, app-store dynamics, churn signals, first-week-experience quality. Pairs with engineering's engineering-side mobile-store-reviewer.