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 commands/ackeskin/contexture/checkpointgit clone --depth 1 https://github.com/AcKeskin/contextureWhat 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 | $0.00061 | $0.00371 |
| Opus 5 | $0.00030 | $0.00186 |
| Sonnet 5 | $0.00012 | $0.00074 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
checkpoint 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 yesterday.
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.
What it actually says
Run the checkpoint skill.
Forms:
/checkpoint— auto-detect the scope and audit at that zoom./checkpoint --scope diff— fit on a change: runs/code-review(correctness) and a fit-pass ("does this serve the intent and cohere with the whole"), in one report./checkpoint --scope module— the post-build checkpoint over the just-built module(s): drift-from-intent, integration-fit (do the pieces cohere), continue-or-kill, lessons./checkpoint --scope corpus— the history + organ-surface audit (decision integrity, intent-vs-shipped, uncaptured lessons, consolidation; organ overlap, dead config, pipeline gaps, vision drift) viaretrospect-core.
Auto-detect: a diff/PR in play → diff; a just-built / named module → module; no target → corpus; ambiguous → asks once. The resolved scope is shown in the report header so you can correct it.
Findings render as one batch (the batched output contract); you pick which to apply in a single pass; each routes to /capture / /memory-audit / a proposals/ stub / a direct edit. Never fixes in place, never auto-fires.
See ~/.claude/skills/checkpoint/SKILL.md for the full procedure (scope resolution, the per-scope passes, the batch-then-apply flow).
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.
- yesterday First seen · 19 lines · 61 tokens per session scan A bd2a8484a2b7
checkpoint is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 371 once invoked, about $0.0003 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 commands, from other repositories
translate-review-to-single-human
Translate a multi-reviewer code review into a single human-voice GitHub PR comment.
address
Address code review feedback — corroborate, validate, and implement changes from a review's final.md.
map
Generate a Code Review Map to help navigate large, complex changesets.
review
Run an AI-powered multi-agent code review on your changes.
sync-reviewers
Sync reviewer metadata from markdown files to reviewers-meta.json for the dashboard.
post
Post the current OCR review to a GitHub PR.