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/sharpen-improve)<a href="https://agentmods.dev/commands/axiomantic/spellbook/sharpen-improve"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/sharpen-improve/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/sharpen-improve"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/sharpen-improve.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 | $0.00040 | $0.01217 |
| Opus 5 | $0.00020 | $0.00609 |
| Sonnet 5 | $0.00008 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00122 |
Grade A, and why
sharpen-improve 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MISSION
Take an ambiguous prompt and produce a sharpened version where an LLM executor would not need to guess on any material decision. Preserve the author's intent while adding precision.
Invariant Principles
- Preserve intent, add precision: Sharpening means clarifying, not rewriting purpose.
- Ask before inventing: If context doesn't resolve ambiguity, ask the author.
- Minimize changes: Touch only what's ambiguous. Leave clear sections alone.
- Document every change: Author must understand what changed and why.
- No scope creep: Adding clarification is not adding features.
Protocol
Phase 1: Audit First
Run the audit protocol from /sharpen-audit internally. Use findings as your working document. Do not output the audit report.
Phase 2: Triage Findings
Categorize each finding:
| Category | Action |
|---|---|
| Resolvable from context | Infer the answer, note source |
| Resolvable from conventions | Apply common convention, note assumption |
| Requires clarification | Generate question for author |
If no findings: proceed directly to Phase 5, outputting the prompt unchanged with an empty change log.
Phase 3: Clarification Round (if needed)
If any findings require clarification:
## Clarification Needed
Before I can sharpen this prompt, I need answers to:
1. **[Finding ID]**: [Original ambiguous text]
Question: [Specific question]
My guess if unanswered: [what I'd assume]
2. ...
Please answer these, or say "use your best judgment" for any you want me to infer.
Wait for author response before proceeding.
Phase 4: Apply Sharpening
For each finding: locate ambiguous text → draft sharpened replacement → verify intent preserved → log the change.
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 · 135 lines · 40 tokens per session scan A a56b71ba1e28
sharpen-improve is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,217 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 2026-09-03.
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.