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/dyzsasd/dev-loop/playbooksnpx skills add dyzsasd/dev-loop --skill playbooksgit clone --depth 1 https://github.com/dyzsasd/dev-loopWhat 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 | $0.00082 | $0.01107 |
| Opus 5 | $0.00041 | $0.00553 |
| Sonnet 5 | $0.00016 | $0.00221 |
| Haiku 4.5 | $0.00008 | $0.00111 |
Grade A, and why
playbooks 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared playbooks (SH-*)
This directory holds the shared job playbooks: one fixed procedure per file, authored once and
referenced by slug from an agent SKILL's marked job spans — never copied into a SKILL (a per-SKILL copy is a
protocol fork). Every fire loads skills/_constitution.md (the resident invariants) + one job playbook (the
procedure for this fire's task) + the shared playbooks that job references.
This is a reference library, not a launchable loop agent — it has no DEVLOOP_ACTOR, boots nothing, and
is excluded from the agent roster.
Sections: §0a §3 §4 §5a §6 §9 §9c §19 §21a §21b §22
Index
The full library — 17 playbooks. The shared playbooks (SH-*) are referenced from more than one
agent's job spans; the single-job scaffolds (SW/RF/OP/AR/CM-*) each back one steward/agent's one job.
Each row's kind is mechanical (a fixed script) or judgment-scaffold (the envelope is fixed, the
judgment is framed, not replaced). Covers names the governing conventions § where the procedure has one.
Shared (SH-*) — referenced by multiple agents' job spans
| Slug | File | kind | Covers |
|---|---|---|---|
| SH-boot | boot.md |
mechanical | the standard fire boot — §0a steps |
| SH-report | report.md |
mechanical | the durable trail + operator 点评 — §22 close |
| SH-claim-groom | claim-groom.md |
mechanical | pick, claim, and groom the next ticket (the pick order + block bail-shape) |
| SH-file-ticket | file-ticket.md |
mechanical | file one well-scoped ticket — §6 / §5a / §4 / §21b / §19 |
| SH-verify-close | verify-close.md |
mechanical | verify In Review → Done, or close + follow-up — §3 / §21a |
| SH-block-park | block-park.md |
mechanical | resolve / route / park a blocked ticket — §9 / §9c |
| SH-split-gate | split-gate.md |
mechanical | is the two-tier Dev split active? (the split charter) |
| SH-fire-start | fire-start.md |
mechanical | reclaim orphans + merge eligible loop PRs (the fire-start merge pass) |
| SH-ship | ship.md |
mechanical | implement, gate, self-review, ship, smoke, hand off (the canonical Step 0–7 ship sequence) |
| SH-read-implement | read-implement.md |
mechanical | resolve the Design pointer, then ship to it (junior's read-and-implement) |
| SH-design-delegate | design-delegate.md |
judgment-scaffold | author the module design, stage junior children — §21a |
| SH-bug-hunt | bug-hunt.md |
judgment-scaffold | the QA bug-discovery scaffold — §4 / §5a / §19 |
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- article.md 7.4 KB
- audit.md 7.1 KB
- block-park.md 3.7 KB
- boot.md 3.1 KB
- bug-hunt.md 4.6 KB
- claim-groom.md 3.6 KB
- design-delegate.md 6.5 KB
- file-ticket.md 3.1 KB
- fire-start.md 4.5 KB
- ops-poll.md 7.5 KB
- read-implement.md 4.5 KB
- report.md 2.5 KB
- retro.md 9.3 KB
- ship.md 8.5 KB
- split-gate.md 1.7 KB
- sweep.md 10.0 KB
- verify-close.md 3.7 KB
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 · 60 lines · 82 tokens per session scan A 5c732f44a46c
playbooks is a skill published in the GitHub repository dyzsasd/dev-loop (5 stars, last pushed 5d ago), licensed MIT. It adds 82 tokens to every session and 1,107 once invoked, about $0.0004 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…