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 agentmods add skills/vrennat/developersdevelopers/verification-before-completionnpx skills add vrennat/developersDevelopers --skill verification-before-completiongit clone --depth 1 https://github.com/vrennat/developersDevelopersWhat 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 | $0.00035 | $0.00354 |
| Opus 5 | $0.00017 | $0.00177 |
| Sonnet 5 | $0.00007 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00035 |
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 yesterday.
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
Verification Before Completion
Fires when Claude is about to claim "done", "fixed", "passing", "ready", or any equivalent. Before any such claim, evidence must be produced. A claim is either about a gate ("tests pass") or about behavior ("the handler now rejects expired tokens", "this is equivalent to the old path"). Gates need a green command; behavior needs ground truth.
Procedure
- Identify the relevant verification command (typecheck, test, build, lint — whichever matches the claim).
- Run it. Capture the output.
- Pass: include the output verbatim in the response, then make the claim.
- Fail: do NOT claim done. Surface the failure. Continue work.
- For a claim about what the code does (not just a green gate): re-read the actual source you are asserting about before claiming. Do not trust your earlier summary or memory of it. Equivalence claims ("same as before", "matches the spec") are testable — prove them: diff the two, run both, compare output.
Example
Bad: "Tests are passing now."
Good:
$ bun run test:run
✓ src/lib/foo.test.ts (12)
Test Files 1 passed (1)
Tests 12 passed (12)
Tests pass.
Behavior claim — bad: "The webhook now verifies signatures." Good: re-open the handler, confirm verifySignature(raw) runs before JSON.parse, quote the lines, then claim.
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.
- yesterday First seen · 32 lines · 35 tokens per session scan A 97dbb999441d
verification-before-completion is a skill published in the GitHub repository vrennat/developersDevelopers (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 354 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…