Borrowing it
Nothing to install: this file belongs to doidor/agentrig. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/doidor/agentrig/main/.agents/skills/self-verify/SKILL.mdgit clone --depth 1 https://github.com/doidor/agentrigWrote 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/doidor/agentrig/self-verify)<a href="https://agentmods.dev/skills/doidor/agentrig/self-verify"><img src="https://agentmods.dev/badge/skills/doidor/agentrig/self-verify/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/doidor/agentrig/self-verify"><img src="https://agentmods.dev/badge/skills/doidor/agentrig/self-verify.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 | $0.00023 | $0.00343 |
| Opus 5.5 | $0.00009 | $0.00137 |
| Sonnet 5.5 | $0.00005 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
self-verify 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 29d 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.
What it actually says
Self-verify
- Read
AGENTS.mdCommands as the source of truth. Before editing, run the available build, test, and lint commands or, when a full baseline is too costly, the smallest relevant check. Record the exact command and observed result: a feature starts from green, while a fix may start from a known red failure. If a check cannot run, record why rather than inventing a result. - After changing behavior, run focused checks and the available repository commands. For an asynchronous check, trigger or await a result for the current worktree or commit, then inspect the output; an earlier green result is not evidence for these changes.
- If a check is red or behavior changed unintentionally, fix the root cause and rerun. Stop after three unsuccessful iterations. If a change needs a human decision or the checks remain red or unavailable, report the exact failure, attempts, and blocker; never claim verification or request approval on a known broken change.
- Compare baseline to after results explicitly, check the diff for unrelated changes, and report any check you could not run. When a new gotcha arises, record it in an existing wiki or knowledge base; if none exists, report its symptom and supporting evidence to the human. Do not install a wiki just for this. Hand off to independent review only when the required verification has converged.
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.
- 29d ago Changed · -25 lines · -23 tokens per session bb2dc3517706
- 2mo ago First seen · 50 lines · 46 tokens per session scan A bd7202272a8e
self-verify is a skill published in the GitHub repository doidor/agentrig (5 stars, last pushed 28d ago), licensed MIT. It adds 23 tokens to every session and 343 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.