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 skills add axiomantic/spellbook --skill dedupegit 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/skills/axiomantic/spellbook/dedupe)<a href="https://agentmods.dev/skills/axiomantic/spellbook/dedupe"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/dedupe/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/skills/axiomantic/spellbook/dedupe"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/dedupe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.02448 |
| Opus 5.5 | $0.00030 | $0.00979 |
| Sonnet 5.5 | $0.00015 | $0.00490 |
| Haiku 4.5 | $0.00007 | $0.00245 |
Grade A, and why
dedupe 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 1mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The dedupe skill identifies and reconciles semantically duplicated prose across a corpus of instructional markdown files (skills, commands, AGENTS.md, design notes). It produces a per-pair verdict drawn from a fixed five-element taxonomy — EXTRACT, KEEP-placement, KEEP-reinforcement, KEEP-contextual, RECONCILE-drifted — and an applyable consolidation plan. The skill does not use lexical or embedding similarity as a primary signal; the authoritative judgment is a counterfactual LLM classification of whether one block can be deleted without information loss.
The five verdict names appear above for orchestration; their full definitions, semantics, and INLINE-MANDATORY interaction live in references/verdict-taxonomy.md.
Invariant principles
-
Analyze is an LLM judgment loop, not lexical similarity. Candidate narrowing (heading-bucket plus optional LLM-triage cross-bucket) is a recall filter, not the verdict. Every surviving pair is judged by a per-pair counterfactual classifier dispatch. See
references/counterfactual-prompt.md. -
Mechanical safety-marker predicate runs before the LLM safety screen. A regex-based predicate force-marks blocks containing INLINE-MANDATORY safety markers, short-circuiting the classifier to KEEP-contextual with
inline_mandatory=true. The pattern table is the canonical source inreferences/safety-markers.md; the orchestrator applies those patterns inline via harness Grep/Read, never via a compiled engine. -
Structural-template heading allowlist short-circuits intra-bucket pairs. Pairs whose heading-topic bucket key (derived per
references/segmentation-protocol.md§3) matches a slot in spellbook's canonical skill-/command-authoring template (e.g.,invariant principles,inputs,outputs,self-check,prerequisite verification, numberedphase Nheadings) resolve toKEEP-placementwithsource=structural_templatewithout classifier dispatch. The allowlist and its phase-name regex patterns live inreferences/template-headings.md. Cross-bucket triage pairs are exempt from this floor so RECONCILE-drifted findings remain detectable.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 123 lines · 75 tokens per session scan A 0abd8992ef19
dedupe is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 2,448 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
bundle-safety
Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.