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/theclaymethod/artifactureWrote 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/theclaymethod/artifacture/project-recap)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/project-recap"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/project-recap/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/theclaymethod/artifacture/project-recap"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/project-recap.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 | $0.00010 | $0.00331 |
| Opus 5.5 | $0.00004 | $0.00132 |
| Sonnet 5.5 | $0.00002 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
project-recap 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 15d 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.
This is a copy
86% identical to project-recap — 62 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Load SKILL.md and cards/project-recap.md.
Resolve $1 as a history window: 2w → two weeks, 30d → thirty days, 3m → three months. Otherwise treat it as context and use two weeks.
- Read the project README, package manifest, and relevant change notes.
- Inspect
git log --oneline --since=<window>,git log --stat --since=<window>, andgit status. Follow recent changes into the entry points, modules, and contracts that explain the current system. - Read relevant plans, ADRs, commit/PR descriptions, and available session context for recorded decisions. A TODO or unmerged branch is evidence of an item, not proof of its current status.
- Keep a fact sheet linking every displayed claim to command output or file:line. Do not infer rationale, ownership, health, or completion from activity alone.
Compose the narrative in cards/project-recap.md: purpose, current architecture, meaningful recent changes, unresolved decisions, and the contracts needed to resume work. Use DiagramCanvas through the diagram card. State blockers and follow-up actions directly with their evidence; omit unsupported health counts, severity badges, and generic dashboards.
Use the default ISO preset. Author MDX/TSX, export to ~/.agent/diagrams/<slug>-project-recap.html, and complete references/verification.md. Open the result and report its source, HTML, final report, and unresolved claims.
$@
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.
- 15d ago Changed d93d42923ff4
- 16d ago Changed c4771a3d09af
- 1mo ago Changed · -52 lines · -13 tokens per session 4512551b6c8a
- 1mo ago First seen · 70 lines · 23 tokens per session scan A 196fd53c2d39
project-recap is a command published in the GitHub repository theclaymethod/artifacture (3 stars, last pushed 5d ago), licensed MIT. It adds 10 tokens to every session and 331 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to project-recap, differing in 62 lines, and is treated as a copy.
Other commands, from other repositories
octo-schedule
Manage scheduled workflow jobs for the Claude Octopus scheduler.
octo-scheduler
Manage the Claude Octopus scheduled workflow runner daemon.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
next
Read the active sprint’s current status. Refresh stale compilation using grainulator compile --dir or grainulator.compile. Use the resulting nextactions with the user’s current scope and authorization. Output only the two Auto and Manual lists below, with no recap, status counters or offer to continue. Continue useful…
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.