Borrowing it
Nothing to install: this file belongs to Koroqe/OPOS. 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/Koroqe/OPOS/main/.claude/skills/check-result/SKILL.mdgit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/check-result)<a href="https://agentmods.dev/skills/koroqe/opos/check-result"><img src="https://agentmods.dev/badge/skills/koroqe/opos/check-result/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/koroqe/opos/check-result"><img src="https://agentmods.dev/badge/skills/koroqe/opos/check-result.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 | $0.00115 | $0.00656 |
| Opus 5.5 | $0.00046 | $0.00262 |
| Sonnet 5.5 | $0.00023 | $0.00131 |
| Haiku 4.5 | $0.00012 | $0.00066 |
Grade A, and why
check-result 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 27d 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
check-result
Follow PROCESS.md (authoritative). Quick facts:
- Caller = the maker (any agent, or the steward). Checker = a fresh
result-checkersubagent viaTask(subagent_type: result-checker), never the maker's own context. - Write the claim as one falsifiable sentence and say how you produced it, so the checker can pick a different method. Vague claims ("it works") are rejected — rewrite them first.
- Independent methods by risk: R0 — none required; R1 "done" — 1; R2 — at least 2; negative claims
about documents, money or obligations — every system the fact could live in, plus a behavioural check;
external facts — sources of different types. A process may raise these numbers in its
checker:field. - R2 = two checks.
phase: planbefore the action (what changes, how to roll back, how the result will be verified) andphase: resultafter it. A result FAIL → roll back per the plan. - Only PASS unlocks. FAIL → fix and re-check, or report the true state. UNVERIFIABLE → the action
stays one class higher (R2 is handled as R3) and missing access is filed as a
kind: resource-gap. - The checker never lowers a class. If the claim or plan shows an action of a higher class than the maker assumed (e.g. writing a secret, changing access or a schedule — always R3), the verdict is FAIL.
- Evidence as pointers (path, hash, query, URL, command) — never client figures, correspondence or personal data copied into an issue or chat.
- A PASS is evidence for the responsible human, not a replacement of their check for client, money and document classes.
- Report the verdict with its method in the issue comment or task report ("verified: , PASS").
- Every run writes
history/YYYY-MM-DD-<run-id>.md.
Policy: company/policies/autonomy-and-decision-rights.md §4.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 27d ago First seen · 35 lines · 115 tokens per session scan A fb1addd3cded
check-result is a skill published in the GitHub repository Koroqe/OPOS (4 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 656 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 2026-09-24.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agentic-verify
Check that a Python change is caught by tests: run every mutant of the changed lines and write tests until they catch them. Reports evidence instead of a diff to read.
verification-strategy
Thorough verification of completed work before declaring done.
verify
Prove a completion claim with fresh evidence before making it — the gate's exit code, the real diff, the remote's checks, the reviewer's verdict.
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.