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/axiomantic/spellbookWrote 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/axiomantic/spellbook/review-plan-completeness)<a href="https://agentmods.dev/commands/axiomantic/spellbook/review-plan-completeness"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/review-plan-completeness/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/axiomantic/spellbook/review-plan-completeness"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/review-plan-completeness.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 | $0.00023 | $0.02060 |
| Opus 5 | $0.00012 | $0.01030 |
| Sonnet 5 | $0.00005 | $0.00412 |
| Haiku 4.5 | $0.00002 | $0.00206 |
Grade A, and why
review-plan-completeness 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 4: Completeness Checks
Verify definitions of done, risk assessments, QA checkpoints, agent responsibilities, and dependency graphs; escalate unverifiable claims.
Invariant Principles
- Subjective criteria are not acceptance criteria — "Works well" or "clean code" are not testable; demand measurable, pass/fail outcomes
- Every phase needs a risk assessment — Undocumented risks are unmitigated risks; absence of risk documentation is itself a finding
- Escalate what you cannot verify — Technical claims requiring execution or external validation must be forwarded to fact-checking, not assumed correct
Definition of Done per Work Item
Work Item: [name]
Definition of Done: YES / NO / PARTIAL
If YES, verify:
[ ] Testable criteria (not subjective)
[ ] Measurable outcomes
[ ] Specific outputs enumerated
[ ] Clear pass/fail determination
If NO/PARTIAL: [what acceptance criteria must be added]
Cluster Collapse Check (work-item granularity)
A candidate cluster is items linked by Depends: edges, a shared deliverable, or
an overlapping file union; apply the per-item revert test within each candidate.
Joint acceptance remains the actual decider.
Apply the revert test PER ITEM: is THIS item independently acceptable — does its
own MEANINGFUL, behavior-level Check: pass with ALL other candidate items
reverted? An item that is NOT independently acceptable must share a work item with
the sibling(s) it MUTUALLY requires — each fails the revert test because of the
other. Take the MAXIMAL set of such
mutually-dependent-for-acceptance items: flag that set as a decomposition finding
and recommend collapsing it into ONE work item with a single joint Check:.
Items that ARE independently acceptable stay separate, even when adjacent to a
joint set — a cluster of one independent item plus a jointly-acceptable pair
splits into the joint pair (flag to collapse) and the independent item (leave
alone). Do NOT require that NONE be independent before flagging; a mixed cluster
still has a joint subset to collapse.
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 Changed · -1 lines 5a2cb97e8e00
- 5d ago First seen · 240 lines · 23 tokens per session scan A 7e20d4b653a4
review-plan-completeness is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 2,060 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 2026-09-03.
Other commands, from other repositories
subagent-implementation
Orchestrate implement→review subagent loop until task complete. Reads the approved spec, writes a thin brief to .claude/.scratchpad/, dispatches fresh-context subagents, loops until reviewer signs off, commits per green iteration, then updates repo docs.
documentation
Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
integrate
Analyze and enhance AI artifacts to leverage Subcog memory effectively.
add-command
Add a new slash command to the current plugin.