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 JeremyDev87/codingbuddy --skill verification-before-completiongit clone --depth 1 https://github.com/JeremyDev87/codingbuddyWrote 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/jeremydev87/codingbuddy/verification-before-completion)<a href="https://agentmods.dev/skills/jeremydev87/codingbuddy/verification-before-completion"><img src="https://agentmods.dev/badge/skills/jeremydev87/codingbuddy/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/jeremydev87/codingbuddy/verification-before-completion"><img src="https://agentmods.dev/badge/skills/jeremydev87/codingbuddy/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 | $0.00038 | $0.01692 |
| Opus 5.5 | $0.00015 | $0.00677 |
| Sonnet 5.5 | $0.00008 | $0.00338 |
| Haiku 4.5 | $0.00004 | $0.00169 |
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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Overview
Claiming success without evidence is guessing. "It should work" is not verification.
Core principle: ALWAYS run verification commands and confirm output before claiming work is complete. Evidence before assertions.
Violating the letter of these checks is violating the spirit of quality.
The Iron Law
NO SUCCESS CLAIMS WITHOUT RUNNING VERIFICATION COMMANDS
If you haven't seen passing output with your own eyes, you cannot claim it works.
No exceptions:
- Don't say "tests should pass" — run them
- Don't say "build looks fine" — build it
- Don't say "no lint errors" — lint it
- Don't say "changes look good" — diff them
When to Use
Always, before:
- Claiming work is "done" or "complete"
- Committing code
- Creating pull requests
- Closing issues
- Reporting success to teammates
- Moving to the next task
Use this ESPECIALLY when:
- Under time pressure (rushing guarantees missed issues)
- Changes seem trivial ("just a typo" can break builds)
- You've made multiple changes across files
- Refactoring existing code
- Fixing bugs (verify the fix AND no regressions)
Don't skip when:
- Change seems too small to break anything (small changes break things)
- You're confident it works (confidence ≠ evidence)
- You "already tested manually" (manual ≠ systematic)
- CI will catch it (catch it NOW, not after push)
The Four Phases
You MUST complete all four phases before claiming completion. Order matters.
Phase 1: Test Execution
Run ALL relevant tests, not just the ones you think matter.
# Run tests for affected area
npm test -- --coverage path/to/affected/
# OR
yarn test path/to/affected/
# Run full test suite if changes are cross-cutting
npm test
Verify:
- All tests pass (zero failures)
- No test warnings or errors in output
- Coverage hasn't decreased
- New code has corresponding tests
- No skipped tests you forgot to unskip
Test fails? Fix it. Do NOT proceed to Phase 2.
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 · 235 lines · 38 tokens per session scan A e68e49eb9c9c
verification-before-completion is a skill published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 1,692 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
fix-issue
Resolve a GitHub issue end to end, from reading the issue through to opening a pull request. Use when the user names an issue number to fix.
fix-issue
Investigates and fixes a GitHub issue. Use when given an issue number or URL, or when the user says 'fix issue'.
resolve-conflicts
Resolves an in-progress git merge or rebase conflict by recovering each side's intent from commits, PRs, and issues. Use when a merge or rebase stops on conflicts, or when the tree contains conflict markers.
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
explain-issue
Explain a GitHub issue: the background problem and the proposed solution.
michel-monitor-pull-request-github-actions
Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment. Invoke whenever Michel's CI monitor loop triggers with anyfailure, stuck, or nottriggered — the bash loop already handles pending and allgreen silently, so…