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 skills add fall-out-bug/sdp --skill reviewgit clone --depth 1 https://github.com/fall-out-bug/sdpWrote 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/skills/fall-out-bug/sdp/review)<a href="https://agentmods.dev/skills/fall-out-bug/sdp/review"><img src="https://agentmods.dev/badge/skills/fall-out-bug/sdp/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/skills/fall-out-bug/sdp/review"><img src="https://agentmods.dev/badge/skills/fall-out-bug/sdp/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 | $0.00025 | $0.02555 |
| Opus 5.5 | $0.00010 | $0.01022 |
| Sonnet 5.5 | $0.00005 | $0.00511 |
| Haiku 4.5 | $0.00003 | $0.00255 |
Grade A, and why
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 2mo 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review
CLI:
sdp quality all| LLM: Spawn all 7 specialist subagents with risk-based depth allocation
Comprehensive multi-agent quality review. All 7 reviewers always spawned; risk patterns determine depth, not presence.
All 7 Reviewers Always Spawned
Base contract: qa, security, devops, sre, techlead, docs, promptops — always present in verdict JSON.
Risk patterns determine review depth, not reviewer presence.
Risk-Based Depth Allocation
LOC tiers set baseline depth; risk patterns override for specific files:
LOC tiers (baseline):
| LOC Range | Deep Reviewers |
|---|---|
| < 50 | qa, techlead |
| 50–200 | qa, security, techlead |
| > 200 | all 7 |
Risk patterns (additive override by file path):
| Pattern | Extra Deep Reviewers |
|---|---|
**/auth/**, **/crypto/** |
security, qa |
**/.github/workflows/**, **/ci/** |
devops, sre |
**/migrations/**, **/db/** |
sre, security |
Full config: .sdp/config.yml under review section.
Flag Overrides
| Flag | Behavior |
|---|---|
--full |
All 7 reviewers with full depth |
--quick |
All 7 reviewers, but only 2-3 do deep review (rest rubber-stamp) |
EXECUTE THIS NOW
When user invokes @review F{XX}:
- Run CLI:
sdp quality all - Determine depth: Match risk patterns to identify which reviewers get deep focus (rest get rubber-stamp).
- Spawn all 7 subagents IN PARALLEL (use your platform's subagent spawn). DO NOT skip.
All 7 roles always spawned: qa, security, devops, sre, techlead, docs, promptops
Per-subagent task template (replace F{XX}, round-N, {role}):
5-step evaluation structure:
- SCOPE: What files/packages does this feature touch?
- RISK MAP: Top 3 risk areas for your domain ({role}) in this scope?
- EVIDENCE: For each risk, what did you find? (file:line, test name, config entry)
- SEVERITY: P0 = exploitable in production. P1 = breaks on edge case. P2 = maintenance debt. P3 = style.
- VERDICT: PASS if max severity ≤ P2. FAIL if any P0/P1.
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.
- 2mo ago First seen · 216 lines · 25 tokens per session scan A 504da7179d99
review is a skill published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 2,555 once invoked, about $0.0001 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 skills, from other repositories
norma-workflow
Run every coding task through Norma's deterministic checks and record the outcome to the audit trail. Use whenever you create or modify code in a workspace connected to the Norma MCP server, when asked to review code against organization standards, or when asked to work through the repository's open issues.
Tech Debt Auditor
Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.
Unit Test Improver
Reviews existing unit tests for gaps, weak assertions, and missing edge cases, then rewrites them to be more robust.
umbra-trust-review
Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.
uncle-bob-craft
Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.