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 wrg32786/aigent-os --skill honesty-checkgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/honesty-check)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/honesty-check"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/honesty-check/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/wrg32786/aigent-os/honesty-check"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/honesty-check.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 96 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 | $0.00065 | $0.01361 |
| Opus 5.5 | $0.00026 | $0.00544 |
| Sonnet 5.5 | $0.00013 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
Honesty Check 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honesty Check
Before saying "done", "shipped", "complete", or "ready for review" — run this checklist. The standard: the principal should never be surprised later by something the agent knew at the time. If known, told.
When to use
- About to declare a piece of work complete
- About to post "PR ready for review" / "fix shipped"
- After any non-trivial fix, port, refactor, or feature
- Triggered by Caddy on prompts like: "done", "shipped", "complete", "ready for review", "PR ready", "all good", "fix is in", "wrapped up", "task complete"
The ledger (volunteer ALL that apply, even unasked)
1. What changed AND what didn't
- Files modified with 1-line summary each
- The "untouched" section — equally important. What stayed the same that someone might assume changed?
2. Anything noticed but not fixed
- Adjacent bugs you saw but didn't address (out of scope)
- Tech debt encountered in the same file
- Failing tests that were already failing
- Dead code, stale comments
3. Any remaining uncertainty after verification
- "I tested case X and Y. Case Z I could not reproduce locally — possible cause is W."
- "Verification passed at runtime but I did not test the recovery path."
4. Any tradeoff made on the principal's behalf
- Simplicity over flexibility ("could have made this configurable; chose constant for now")
- Small fix over refactor ("the regex works but the right fix is a parser")
- Speed over thoroughness ("I didn't update the 3 callers in test files; production callers all updated")
5. Any place you stopped short of what was asked, and why
- "You asked for end-to-end; I covered A→B but B→C is in a separate file owned by another agent"
- "Spec said add the 3 fields; I added 2 because the 3rd has no migration path yet"
6. Any cost/implication the principal might not have anticipated
- Deploy required to take effect
- API change → callers will break until updated
- Migration needed before next release
- Paid integration tier triggered
- Cache invalidation required
- New env var needed
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 · 121 lines · 65 tokens per session scan A 9d5865580c50
Honesty Check is a skill published in the GitHub repository wrg32786/aigent-os (23 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,361 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 2026-09-01.
Other skills, from other repositories
nav-pilot
Dispatch a Navigator task doc to Pilot as a labeled GitHub issue. Use when user says "dispatch TASK-XX to Pilot", "hand off to Pilot", "send to Pilot", or "queue for Pilot". One-way handoff (Navigator authors the spec, Pilot executes autonomously).
graphify
Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…
insights
Use when the user types /weekly or /monthly, asks for a weekly or monthly journal review or retrospective, asks 'how was my week' or 'how was my month', or wants trends, anomalies, or patterns across recent journal entries. Also fires when regenerating an insight report for a past week or month. NOT for writing…
setup-brain
Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.
second-brain-mapping
Use when the user wants to map or remap their second brain, refresh the vault's queryable metadata index, extract structured frontmatter from typed notes (books, meetings, people, journals, goals), fill wikilink gaps, or surface cross-type insights and patterns no single file shows. Triggers: /second-brain-mapping…
sunday-review
Use when the user asks for the weekly meta-review or Sunday wrap-up of their week and vault: says /sunday, /sunday-review, 'let's do the weekly review,' 'Sunday review,' 'review my week,' 'weekly retro,' 'week in review,' 'end-of-week review,' or wants journals, patterns, vault health, and stale decisions reviewed…