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 verifying-hunchesgit 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/verifying-hunches)<a href="https://agentmods.dev/skills/axiomantic/spellbook/verifying-hunches"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/verifying-hunches/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/verifying-hunches"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/verifying-hunches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 120 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00134 | $0.01455 |
| Opus 5.5 | $0.00054 | $0.00582 |
| Sonnet 5.5 | $0.00027 | $0.00291 |
| Haiku 4.5 | $0.00013 | $0.00145 |
Grade A, and why
verifying-hunches 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying Hunches
False confidence is worse than admitted uncertainty. This is very important to my career.
You are here because you're about to claim a discovery. STOP. That's a hypothesis, not a finding.
Invariant Principles
- Hypotheses are not findings. "I think" ≠ "I found". Use precise language.
- Déjà vu means disproven. Same eureka twice? It didn't work before.
- Specificity defeats generalization. State exact claim: location, mechanism, symptom link.
- Falsification before confirmation. Define what DISPROVES the theory first.
- Evidence is behavioral. "Code looks wrong" isn't evidence. "When X, Y instead of Z" is.
Eureka Registry
Track ALL hypotheses. Persist across compaction in /handoff.
| Field | Purpose |
|---|---|
id |
H1, H2, etc. |
claim |
Exact specific claim |
falsification |
What would disprove this |
status |
UNTESTED / TESTING / CONFIRMED / DISPROVEN |
test_results |
prediction vs actual for each test |
Confidence Calibration
| DON'T SAY | SAY INSTEAD |
|---|---|
| "I found the bug" | "Hypothesis: [specific claim]. Testing now." |
| "This is the issue" | "Suspect this code. Need to verify." |
| "Root cause is X" | "Theory: X. Verification: [test]" |
| "I see what's happening" | "Mental model formed. Testing accuracy." |
Specificity Requirements
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 · 159 lines · 134 tokens per session scan A 5b0a4ed4318b
verifying-hunches is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 134 tokens to every session and 1,455 once invoked, about $0.0005 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
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
memory-leak-debug
Diagnose memory leaks in the Qwen Code CLI using heap snapshots and the chrome-devtools CLI. Use when investigating high memory usage, unbounded growth, or suspected object retention issues.
bugfix
Fix a bug from a GitHub issue, following the reproduce-first workflow. Use when the user asks to fix a bug, investigate a GitHub issue, or debug a user-reported problem. Takes a GitHub issue URL or number as input.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.