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 rileyhilliard/agentrc --skill verification-before-completiongit clone --depth 1 https://github.com/rileyhilliard/agentrcWrote 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/rileyhilliard/agentrc/verification-before-completion)<a href="https://agentmods.dev/skills/rileyhilliard/agentrc/verification-before-completion"><img src="https://agentmods.dev/badge/skills/rileyhilliard/agentrc/verification-before-completion/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/rileyhilliard/agentrc/verification-before-completion"><img src="https://agentmods.dev/badge/skills/rileyhilliard/agentrc/verification-before-completion.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 | $0.00035 | $0.00853 |
| Opus 5.5 | $0.00014 | $0.00341 |
| Sonnet 5.5 | $0.00007 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
verification-before-completion 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Core Principle: No completion claims without fresh verification evidence.
The Verification Gate
BEFORE any claim of success, completion, or satisfaction:
Copy this checklist and track your progress:
Verification Checklist:
- [ ] IDENTIFY: What command proves this claim?
- [ ] RUN: Execute the verification command (fresh, complete)
- [ ] READ: Check full output, exit code, failure counts
- [ ] VERIFY: Does output confirm the claim?
- If NO → State actual status with evidence
- If YES → State claim WITH evidence
- IDENTIFY - What command proves this claim?
- RUN - Execute the full verification command (fresh, complete)
- READ - Check full output, exit code, failure counts
- VERIFY - Does output confirm the claim?
- NO → State actual status with evidence
- YES → State claim WITH evidence from step 2-3
Skip any step = invalid claim.
When This Applies
ALWAYS before:
- Claiming "tests pass", "build succeeds", "linter clean", "bug fixed"
- Expressing satisfaction ("Great!", "Done!", "Perfect!")
- Using qualifiers ("should work", "probably fixed", "seems to")
- Committing, creating PRs, marking tasks complete
- Marking a multi-file implementation as complete (dispatch
ce:code-revieweragent) - Moving to next task or delegating work
- ANY statement implying success or completion
Common Verification Requirements
| Claim | Required Evidence | Not Sufficient |
|---|---|---|
| Tests pass | yarn test output: 0 failures |
Previous run, "looks correct" |
| Build succeeds | Build command: exit 0 | Linter clean, "should work" |
| Bug fixed | Test reproducing bug: now passes | Code changed, assumed fix |
| Linter clean | Linter output: 0 errors | Partial check, spot test |
| Regression test works | Red→Green cycle verified | Test passes once |
| Agent task complete | VCS diff shows expected changes | Agent reports "success" |
| Work is complete | Code review via ce:code-reviewer with no unresolved Critical issues |
Self-review, "looks good to me" |
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 · 108 lines · 35 tokens per session scan A d17db85a4dc1
verification-before-completion is a skill published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 8mo ago), licensed MIT. It adds 35 tokens to every session and 853 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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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.