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 | $0.00032 | $0.00681 |
| Sonnet 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 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 — 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.
- 8d 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 (18 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. 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
hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a dbpath field.
operator-scorecard
Three recap modes - default synthesizes agent health, community growth, and economic activity into a was-it-worth-it verdict; ops recaps what shipped and failed; push ranks push impact.
github-monitor
Watch your GitHub repos across four views - a combined urgency monitor (stale PRs, new issues, releases), a new-issue triage queue, a release upgrade digest, or your own opened-PR tracker.
heartbeat
Ambient fleet-health check that surfaces anything worth attention (default), or an on-demand priority brief - the 3 things to focus on, why now, and what moved (var=brief).
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
idea-pipeline
Execution-gap audit - cross-references the startup idea backlog against shipped skills, prototypes, and cross-repo PRs, surfacing the top 3 ideas to build next by narrative and operator fit.