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 skills/urrhb/agentflow/sdlc-stopnpx skills add UrRhb/agentflow --skill sdlc-stopgit clone --depth 1 https://github.com/UrRhb/agentflowWhat 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 | $0.00032 | $0.00725 |
| Opus 5 | $0.00016 | $0.00362 |
| Sonnet 5 | $0.00006 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
sdlc-stop 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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-stop
Gracefully shut down the AgentFlow pipeline.
Plugin Mode Additions
In plugin mode, also:
- Call TeamDelete("sprint-team") to clean up the agent team
- Workers receive shutdown signal via SendMessage (faster than Asana read)
- No need to instruct user about crontab — plugin handles scheduling
Process
Step 1: Signal pausing
Find the pinned Status task across all [SDLC] projects.
Post comment: [SYSTEM:PAUSING] Graceful shutdown initiated. Active workers will finish their current stage. No new tasks will be dispatched.
Step 2: Drain active work
Check all tasks in Research/Build/Review/Test/Integrate stages:
For tasks with [BUILD:STARTED] and recent heartbeat (< 10 min):
- Leave them alone — the worker is still active
- Report: "Waiting for <task_code> to finish (worker )"
For tasks in Research or Build WITHOUT [BUILD:STARTED] (not started yet):
- Move back to "1 - Backlog"
- Clear slot:
[SLOT:T<N>]→[SLOT:--] - Reset stage:
[STAGE:X]→[STAGE:Backlog] - Clean up git worktree if it exists:
git worktree remove feat/<task-code>-<slug> --force
For tasks in Review/Test that are waiting (no worker actively processing):
- Move back to "1 - Backlog"
- Clear slot
- Reset stage
- Clean up git worktree if it exists:
git worktree remove feat/<task-code>-<slug> --force
Step 3: Wait for active workers
Report which tasks are still being worked on.
Tell the user: "Active workers are finishing. The system will be fully paused when all active work completes. You can check your Kanban board for current status."
Step 4: Post paused status
Update the Status task:
[SYSTEM:PAUSED]
Graceful shutdown complete — <timestamp>
Tasks returned to Backlog: <N>
Tasks still completing: <N> (if any workers were mid-build)
To resume: run /sdlc-orchestrate
Step 5: Disable crontab (instruct user)
Tell the user:
To fully stop the orchestrator, comment out or remove the crontab entry:
crontab -e
# Comment out: */15 * * * * /usr/local/bin/claude -p "Run /sdlc-orchestrate" ...
To resume later, uncomment it and run /sdlc-orchestrate once to kick things off.
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.
- 2d ago First seen · 84 lines · 32 tokens per session scan A ac995348c291
sdlc-stop is a skill published in the GitHub repository UrRhb/agentflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 725 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…