Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/saitarrun/Devforge-ainpx agentmods add commands/saitarrun/devforge-ai/sdlc-verifyWrote 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/commands/saitarrun/devforge-ai/sdlc-verify)<a href="https://agentmods.dev/commands/saitarrun/devforge-ai/sdlc-verify"><img src="https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-verify/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/commands/saitarrun/devforge-ai/sdlc-verify"><img src="https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-verify.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 | $0.00033 | $0.00737 |
| Opus 5.5 | $0.00013 | $0.00295 |
| Sonnet 5.5 | $0.00007 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
sdlc-verify 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-verify — Phase 3: Verify
Security audit and performance validation. Reads the build handoff for a clean context window, then invokes security-engineer (always) and performance-engineer (scope-gated).
Step 1: Load Handoff (Clean Context)
Read ./projects/<feature>/handoffs/build-handoff.md as the FIRST step. This is the sole context source — do not carry forward the Build phase conversation history.
Step 2: Read Scope
Read ./projects/<feature>/scope.json:
needs_pentest— whether security-engineer should run pentest sectionneeds_performance_audit— whether to invoke performance-engineer
Step 3: Invoke Agents
Agent 1: security-engineer (ALWAYS)
Invoke: security-engineer
Context provided:
- ./projects/<feature>/handoffs/build-handoff.md
- ./projects/<feature>/implementation-log.md
- ./projects/<feature>/scope.json (for needs_pentest flag)
The agent runs SAST, OWASP Top 10, dependency scan, and security headers check.
If needs_pentest: true — also runs DAST and penetration testing scenarios.
Output: ./projects/<feature>/docs/security-report.md
Wait for security-engineer to complete.
Agent 2: performance-engineer (only when needs_performance_audit: true)
Invoke: performance-engineer
Context provided:
- ./projects/<feature>/handoffs/build-handoff.md
- ./projects/<feature>/implementation-log.md
- ./projects/<feature>/grill-summary.md (for scale targets)
The agent runs profiling, benchmarking, and produces optimization recommendations.
Output: ./projects/<feature>/docs/performance-report.md
If needs_performance_audit: false — skip this agent entirely.
Wait for performance-engineer to complete (if invoked).
Step 4: Display Completion
✅ Verify Phase Complete!
Agents invoked:
1. security-engineer → security-report.md [always]
2. performance-engineer → performance-report.md [if needs_performance_audit]
Artifacts:
./projects/<feature>/docs/
├── security-report.md
└── performance-report.md (if applicable)
Quality Gates:
✅ No Critical/High security findings unresolved
✅ OWASP Top 10 fully reviewed
✅ Dependency CVEs patched or accepted
[✅ Performance within targets] (if applicable)
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 · 93 lines · 33 tokens per session scan A 377a58b5ae54
sdlc-verify is a command published in the GitHub repository saitarrun/Devforge-ai (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 737 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 2026-08-31.
Other commands, from other repositories
doctor
Check OCR installation and verify all dependencies are available.
doctor
Run llm-redact's read-only diagnostics (config, build, vault, extras, posture).
fix-risks
Use to fix risk findings via the fix verb (improve → oop-orchestrator fix mode) — the gated FIX action the /audit report's Recommended Actions hands off to. Resolves an entity selection against the glossary and applies the smallest corrective refactor per in-scope entity, OOP first, verified with the project's own…
brain-repair
Diagnose failed BRAIN alpha results and propose a repair batch.
bottleneck-detect
Analyze performance bottlenecks in swarm operations and suggest optimizations.
sparc-refinement-optimization-mode
🧹 Optimizer - You refactor, modularize, and improve system performance. You enforce file size limits, dependenc...