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/axiomantic/spellbook/dedupe-reportgit 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/dedupe-report)<a href="https://agentmods.dev/commands/axiomantic/spellbook/dedupe-report"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/dedupe-report.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.01840 |
| Opus 5 | $0.00019 | $0.00920 |
| Sonnet 5 | $0.00008 | $0.00368 |
| Haiku 4.5 | $0.00004 | $0.00184 |
Grade A, and why
dedupe-report 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 5d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MISSION
Phase 3 of the dedupe skill: consume the verdicts artifact produced by
/dedupe-analyze, render a human-readable markdown report, and drive
per-finding disposition approval via AskUserQuestion.
This command is read-only with respect to the source markdown
tree. The only file it writes is the report artifact itself. It NEVER
edits skill or command files. It NEVER auto-chains to /dedupe-apply.
Part of the dedupe- command family.* Run after /dedupe-analyze.
Run before /dedupe-apply.
Invariant Principles
- Read-only with respect to source files — this phase produces a report; the apply phase produces edits. They are separate, gated by explicit operator invocation.
- No auto-chain to apply —
/dedupe-applyis invoked explicitly by the operator after they review the report. This command never triggers it. - Per-finding disposition is gated — EXTRACT candidates each receive
one
AskUserQuestionprompt. There is no "apply all" affordance at this phase. - Drift is surfaced, never auto-resolved — RECONCILE-drifted findings appear in their own section with no apply option.
No-auto-chain invariant: This command never auto-chains to
/dedupe-apply. The operator explicitly invokes apply only after
reviewing the report and its recorded dispositions. Auto-chaining
would bypass the report-review gate that exists for safety.
Invocation
/dedupe-report <verdicts-path>
<verdicts-path>— the artifact produced by/dedupe-analyze. Required.
Inputs
- The verdicts artifact at
<verdicts-path>. Read it to recover the per-pair findings, the reproducibility footnote, and the resolved seed paths.
If the verdicts artifact records analyze_halted=true, this command
renders only the halt summary section and exits. No EXTRACT candidates
are surfaced; the operator must rerun /dedupe-analyze after
addressing the halt cause.
Phase 3.1 — Aggregate verdicts
Parse the verdicts artifact and group findings by verdict family:
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.
- 5d ago First seen · 211 lines · 38 tokens per session scan A cf9661fedc77
dedupe-report is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,840 once invoked, about $0.0002 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
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
boldguy-linkedin-answer
Draft a LinkedIn comment on a post, referencing the guide's relevant section, in Flow style with AI markers removed.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
sync
Check guide/landing synchronization status.
worktree
Create a git worktree for isolated feature/fix work.