agentflow — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited agentflow (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
AgentFlow turns your existing Kanban board into a fully autonomous AI development pipeline. Instead of building custom orchestration infrastructure, it treats your project management tool (Asana, GitHub Projects, Linear) as a distributed state machine — tasks move through stages, AI agents read and write state via comments, and humans intervene through the same UI they already use.
The result is complete pipeline observability from your phone, free crash recovery (state lives in your PM tool, not in memory), and human override at any point by dragging a card.
Tasks flow through: Backlog, Research, Build, Review, Test, Integrate, Done. Each stage has specific gates. The Kanban board IS the orchestration layer — no separate database, no message queue, no custom infrastructure.
A crontab-driven one-shot sweep runs every 15 minutes. No daemon, no session dependency. If it crashes, the next sweep picks up where it left off because all state lives in your PM tool.
Hard gates (tsc + eslint + tests) run before any AI review, catching roughly 60% of issues at near-zero cost. AI review comes after, as a second layer.
A different AI agent reviews code and must list 3 things wrong before deciding to pass. This prevents rubber-stamp approvals.
Tasks that unblock the most downstream work get built first, automatically computing the critical path.
/spec-to-boardDecomposes a SPEC.md into atomic tasks on your Kanban board with dependencies mapped.
/sdlc-orchestrateDispatches tasks to workers based on transitive priority and conflict detection. Runs as a crontab sweep.
/sdlc-worker --slot <N>Runs a worker in a terminal slot that picks up tasks, builds code, and creates PRs. Run 3-4 workers in parallel.
/sdlc-healthReal-time pipeline status dashboard showing current stage, assigned agent, retry count, and accumulated cost for every task.
/sdlc-stopGraceful shutdown: active workers finish their current task, unstarted tasks return to Backlog.
Create a SPEC.md for your project describing what you want to build.
claude -p "/spec-to-board"This reads your SPEC.md, decomposes it into atomic tasks, maps dependencies, and creates them on your Kanban board.
Open 3-4 terminal windows, each as a worker slot:
# Terminal 2 — Builder
claude -p "/sdlc-worker --slot T2"
# Terminal 3 — Builder
claude -p "/sdlc-worker --slot T3"
# Terminal 4 — Reviewer
claude -p "/sdlc-worker --slot T4"
# Terminal 5 — Tester
claude -p "/sdlc-worker --slot T5"# Add to crontab (runs every 15 minutes)
crontab -e
# Add: */15 * * * * ~/.claude/sdlc/agentflow-cron.sh >> /tmp/agentflow-orchestrate.log 2>&1Open your Kanban board on your phone. Watch tasks flow through the pipeline. Drag any card to "Needs Human" to intervene. Run /sdlc-health for a terminal dashboard.
claude -p "/sdlc-stop"Each stage enforces specific gates before promotion:
tsc + eslint + npm test must all pass (deterministic)Per-task cost tracking with stage ceilings (Sonnet defaults):
Automatic guardrails: warning at $3/$8, hard stop at $10/$20 (Sonnet/Opus) with human escalation.
git revert (new commit, never force-push)/sdlc-stop drains workers, returns unstarted tasks to backlog~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.