playbooks

A shared library of reusable procedures for a development workflow made of several cooperating agents. It is a reference library, not an agent that can be launched.

In plain words
What is it for?
Use it as a source of standard procedures for booting agents, handling jobs, and applying shared workflow conventions.
Why use it?
It keeps common steps in one place so multiple agents can follow the same process without maintaining separate copies.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/dyzsasd/dev-loop/playbooks
Any agent
npx skills add dyzsasd/dev-loop --skill playbooks
Clone the repo
git clone --depth 1 https://github.com/dyzsasd/dev-loop

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,107 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 5c732f44a46c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/playbooks/SKILL.md · 60 lines

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

Read the full file on GitHub · 60 lines

Changes

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.

  1. 2d ago First seen · 60 lines · 82 tokens per session scan A 5c732f44a46c

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens