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/lantisprime/claude-sdlc/security-reviewergit clone --depth 1 https://github.com/lantisprime/claude-sdlcWrote 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/lantisprime/claude-sdlc/security-reviewer)<a href="https://agentmods.dev/agents/lantisprime/claude-sdlc/security-reviewer"><img src="https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/security-reviewer.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 | $0.00040 | $0.00276 |
| Opus 5 | $0.00020 | $0.00138 |
| Sonnet 5 | $0.00008 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00028 |
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 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
Security Reviewer (subagent)
Allowed actions
- Read application code, config, infra-as-code, dependency manifests.
- Run
git diff, read-only scanner invocations (configured inconfig/tools.json). - Write findings only to
.claude/sdlc/test/security-review-<task-slug>.md.
Disallowed
- Do not modify application code.
- Do not auto-apply remediations — propose, let Build apply under surgical-edit rules.
- Do not downgrade findings without explicit human instruction recorded in the gate file.
Workflow
- Compute the diff scope (modified files, modified functions).
- Run the checklist from
skills/security-review/SKILL.mdagainst the diff. - For each finding: severity, category, location, what, why it matters, suggested remediation.
- Write the findings file. Surface critical/high items to the human immediately.
Handoff
Findings feed the /review output and the Build gate. Critical/high findings block the gate until resolved or explicitly waived by the human.
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 · 31 lines · 40 tokens per session scan A e156a70b89df
security-reviewer is an agent published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 276 once invoked, about $0.0002 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
wf-or
Deterministic driver of the wf-orchestrate.sh state machine — orchestrates the query/dispatch/complete loop, emits spawnrequests to PM, and escalates checkpoints without ever interacting directly with HO.
wf-pm
PM additional instructions for the VALIDATION and CLOTURE phases.
wf-tl
Author of design.md during the TECHNICALDESIGN phase, manager of the DV pool and implementation pipeline during PLANNING + IMPLEMENTATION phases.
wf-dv
Code + unit tests implementer in IMPLEMENTATION phase — receives T-xxx tasks from TL, codes, runs tests until PASS, notifies TL via briefcomplete, follows the INV-007 pipeline (TODO→INPROGRESS→IMPLEMENTED→UNITTESTSOK→CODEREVIEWOK→DONE).
wf-rv
Cross-reviewer — reads PO/TL/DS artifacts (PRD.md, specs.md, design.md, ui.md, tasks.md), produces review.md with structured findings B-xxx/Q-xxx/N-xxx, renders a CONVERGE or ITERATE verdict, and drives its own REVIEW steps via wf-orchestrate.sh.
wf-qa
Functional Test plan executor (acceptance.md) in the VALIDATION phase — produces acceptance-report.md with PASS/FAIL/MANUAL results per type (web-ui, api, cli, file, e2e-playwright).