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/decompose-claims)<a href="https://agentmods.dev/commands/axiomantic/spellbook/decompose-claims"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/decompose-claims.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 | $0.00030 | $0.00909 |
| Opus 5 | $0.00015 | $0.00454 |
| Sonnet 5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
decompose-claims 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 8d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompose Claims
Atomic claim decomposition for text and documentation, based on Min et al. (2023) FActScore methodology.
When to Use
- Fact-checking extraction (Phases 2-3) encounters compound claims
- Dehallucination review of design documents or specifications
- Design document review finds dense factual paragraphs
- Any verification task where claims are entangled
When NOT to Use
- Code assertions (use inline verification checklists instead)
- Direct API documentation (already atomic by nature)
- Single-predicate statements (already atomic)
Invariant Principles
- Atomic = one predicate, one subject. "X does Y and Z" is two claims, not one.
- Preserve original meaning. Decomposition must not add or subtract meaning.
- Independence. Each atomic claim must be verifiable without reference to other claims from the same decomposition.
- No interpretation. Decompose what is stated, not what is implied.
Decomposition Protocol
Step 1: Identify Compound Statements
Scan the input text for:
- Conjunctions joining distinct facts ("X and Y", "X but Y", "X while Y")
- Relative clauses adding facts ("X, which does Y")
- Parenthetical additions ("X (using Y)")
- Lists presented as prose ("supports A, B, and C")
- Causal chains ("X because Y, leading to Z")
Step 2: Extract Atomic Claims
For each compound statement, produce atomic claims following this pattern:
| Compound | Atomic Claims |
|---|---|
| "The cache uses Redis and expires entries after 5 minutes" | 1. "The cache uses Redis" 2. "Cache entries expire after 5 minutes" |
| "Authentication is handled by OAuth2, which requires HTTPS" | 1. "Authentication is handled by OAuth2" 2. "OAuth2 requires HTTPS" |
| "The API supports JSON and XML responses with rate limiting" | 1. "The API supports JSON responses" 2. "The API supports XML responses" 3. "The API has rate limiting" |
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.
- 8d ago First seen · 102 lines · 30 tokens per session scan A 989d30223082
decompose-claims is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 909 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
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.