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/ethanaubuchon/dossier-tradecraftWrote 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/ethanaubuchon/dossier-tradecraft/implement)<a href="https://agentmods.dev/commands/ethanaubuchon/dossier-tradecraft/implement"><img src="https://agentmods.dev/badge/commands/ethanaubuchon/dossier-tradecraft/implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ethanaubuchon/dossier-tradecraft/implement"><img src="https://agentmods.dev/badge/commands/ethanaubuchon/dossier-tradecraft/implement.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.03314 |
| Opus 5.5 | $0.00018 | $0.01326 |
| Sonnet 5.5 | $0.00009 | $0.00663 |
| Haiku 4.5 | $0.00005 | $0.00331 |
Grade A, and why
implement 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 7d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are starting an /implement session. The ticket / spec (if provided): $ARGUMENTS
This is the /implement recipe of the dossier-tradecraft framework — Phase 4, feature implementation in a repo. It consumes one ticket and drives it through: branch → plan → code → review → PR. The recipe is thin: it sequences six overridable primitives and hosts the interactive review loop in the main conversation.
Principles
- The spine is the developer's own flow — not superpowers, not TDD. Develop to the plan; tests are written alongside and verified, never test-first. Superpowers / TDD execution are available as project-level execute-step overrides, not the default.
- Ticket-driven entry. v1 assumes a ticket exists (issue# / station ID / spec-path / explicit ask). Writing the ticket is
/decompose's or an ad-hoc job — out of/implement's scope. The bare no-ticket path is deferred. - Thin recipe over overridable primitives. The recipe sequences and branches;
repo-setup,plan-file,agent-review,open-draft-pr,publish-pr,cleanup-artifactsdo the work. Each is project-overridable. - Review on committed work, in a draft PR, behind a human gate. Never review unstaged changes. The draft PR exists before review so the PR-framed reviewer agents have a PR to attach to; the human decides when it's ready-for-humans.
- Squash kills review-iteration noise at draft→ready — not single-commit dogma.
- Dependency-free floor; toolkit ceiling via override.
agent-reviewships a dependency-free reviewer; thepr-review-toolkitpanel is an opt-in override. Nothing beyond dossier-mcp is required. - Repo-shaped. Vault-path is out of v1 —
/implementexpects a git repo.
Workflow
- Load context. Invoke the
load-contextskill (vault grounding: profile, inbox check, project pre-warm). Note the cwd, current branch, and whether a project agent-instruction file (CLAUDE.md, AGENTS.md, etc.) is present — its prose carries per-project conventions (test command, sub-agent routing, PR shape). If the working directory is not a git repo, stop and say so —/implementis repo-shaped in v1.
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.
- 7d ago Changed · +6 lines d7d2b9a5c779
- 27d ago Changed · +4 lines 86cfb91ebdde
- 1mo ago Changed 57ddb7cc66d9
- 1mo ago First seen · 72 lines · 45 tokens per session scan A 1d3c09e936ed
implement is a command published in the GitHub repository ethanaubuchon/dossier-tradecraft (3 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 3,314 once invoked, about $0.0002 per session on Opus 5.5. 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 commands, from other repositories
clean
Tidy and sync — commit changed notes, clear processed Inbox (with approval), and push.
commit-claude-config
Un-ignore and commit the kit config (.claude/, CLAUDE.md, .mcp.json, .gitmodules).
iteration-loop
Run a whole iteration Phase 1→6 autonomously — code-first direction lock with a retained prototype, then execute → close → PR → merge-ready → post-merge close. Optional direction hint and scale S|M|L|XL; explicit autonomous opt-in, no grill-me, no routine confirmation.
speckit.polish
Polish and complete speckit workflow — quality gate, docs, changelog, MR.
review-open-prs
Command "review-open-prs" from The-Artificer-of-Ciphers-LLC/skills-from-the-artificer, covering batch pr review directive — all open prs i did not author, phase a — enumerate target prs & build the queue, phase b — per-pr directive (runs once per queued $pr), 0. context anchoring and 1. preconditions.
review
Recent git commits: !git log --oneline -10.