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/jonase47/ccpr/anchorgit clone --depth 1 https://github.com/jonase47/ccprWhat 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 | $0.00000 | $0.02674 |
| Opus 5 | $0.00000 | $0.01337 |
| Sonnet 5 | $0.00000 | $0.00535 |
| Haiku 4.5 | $0.00000 | $0.00267 |
Grade A, and why
anchor 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/anchor – Anchored State Verification (Docs vs. Implementation)
Checks phase documents against the code they describe, not against other documents. Where
/cross-check compares Markdown to Markdown, /anchor compares a document's declared
anchor_commit to the repository's actual history — the two-stage check design of
docs/adr/ADR-0009-anchored-state-verification.md (both addenda).
Argument: $ARGUMENTS = [optional: projectdir] [--scope ]
- Without argument: operates on
$(pwd). --scope <folder>restricts the run to one phase folder (discovery,concept,validation,architecture,planning,quality,launch,operations).
Prerequisites
- A git repository with at least one commit.
- At least one phase folder under
docs/(discovery/,concept/,validation/,architecture/,planning/,quality/,launch/,operations/). - Not required, but the reason a run reports mostly "not verified": an anchor written on the
phase index via
anchor set(normally done by the freeze hook on a Gate-Go, ADR-0009 Addendum 2).
Lead Agent
Orchestrator runs Stage 1 directly (a mechanical script call, nothing to delegate). Stage 2's per-document judgment can be done by the orchestrator or delegated to code-reviewer / system-architekt for a scope with unfamiliar code — in either case, the agent doing Stage 2 is bound by The agent clause below (§3 is the escalation step, not the clause).
Execution
1. Stage 1 — mechanical delta (no verdict)
Run exactly:
bash ~/.claude/scripts/anchor.sh check [projectdir] [--scope <folder>]
This is the only source for Stage 1 data — do not re-derive the delta by hand (e.g. git diff against a guessed commit). The report already contains, per scope: the resolved
anchor_commit/anchor_date, the last production-code commit, the changed production-code
paths, which document(s) claim each path via covers:, and the full "Affected documents"
list per scope with each document's own status.
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 · 204 lines · 0 tokens per session scan A 539b0fa50b24
anchor is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,674 tokens. 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
drift
Post-implementation spec drift check — verify the implementation matches existing OpenSpec specifications.
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
research
Research a technical or product question.
tidy
Consistency check for non-code repos with INDEX.md hierarchy. Verifies INDEX.md accuracy, MEMORY.md references, orphaned files, stale dates, and WAITING markers.
clean-check
Analyze code for cleanliness issues (unused code, comment quality, formatting, naming, complexity). Delegates to the code-cleanliness agent.
build
Mini spec-first development workflow for well-scoped implementation tasks with human in the loop.