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.
git clone --depth 1 https://github.com/ZSeven-W/dsh-crewWrote 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/zseven-w/dsh-crew/playbook)<a href="https://agentmods.dev/commands/zseven-w/dsh-crew/playbook"><img src="https://agentmods.dev/badge/commands/zseven-w/dsh-crew/playbook.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.01047 |
| Opus 5 | $0.00012 | $0.00524 |
| Sonnet 5 | $0.00005 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
playbook 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- dsh-playbook — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When the user asks how to dispatch work to DSH workers — tier choice, writing a brief, parallelism, verifying results, guardrails — answer from the playbook below. Point to the relevant section rather than reciting it whole.
DSH Crew — Dispatch Playbook
How to delegate work to DSH workers well. The tool descriptions carry the mechanics; this playbook is the decision layer.
1. Choosing a worker
flash — mechanical, well-scoped work:
- Rename a symbol in one or two files and update the obvious call sites.
- Read a config file and report the values of a few keys.
- Add a unit test for an existing function, following the file's existing style.
pro — multi-file work, debugging, design judgment:
- Refactor a module that is used across the repo and update every caller.
- Diagnose a flaky test or a race condition by reading logs and tracing the code.
- Design a new API or file layout with tradeoffs to weigh, then implement it.
When in doubt, start with flash: escalate_on_failure retries a failed blocking flash run once on pro, so evidence, not guesswork, decides.
worker="agy" / worker="grok" is explicit opt-in. Set it only when the user explicitly asks for that CLI, never as a default. Two caveats to tell the user: grok refuses to start repo-local MCP servers in untrusted folders (global installs are unaffected; change directory or pass --trust), and agy runs with full approval because it has no workspace-scoped permission mode.
2. Writing the brief
The worker has zero conversation context. Every task string must be self-contained:
- Absolute paths for every file and directory involved.
- Exact acceptance criteria: what must be true when done, and how to verify it.
- What NOT to touch (generated files, unrelated modules, lockfiles).
- Never commit, push, or publish unless the user explicitly authorized it — write that into the brief.
Bad: "fix the auth bug". Good: "In /abs/path/repo/src/auth.ts the token refresh throws on 401 when the session expires; make it retry once and fail loudly, add a test in /abs/path/repo/test/auth.test.ts, and run npm test. Touch only auth.ts and its test. Do not commit."
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.
- 8d ago First seen · 65 lines · 24 tokens per session scan A 839d9de61098
playbook is a command published in the GitHub repository ZSeven-W/dsh-crew (134 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 1,047 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
memory-report
Calibration + inventory check of your causal memory (prediction ledger accuracy, what you know).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.