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/zszz3/agentrecall/verification-before-completionnpx skills add zszz3/AgentRecall --skill verification-before-completiongit clone --depth 1 https://github.com/zszz3/AgentRecallWrote 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/zszz3/agentrecall/verification-before-completion)<a href="https://agentmods.dev/skills/zszz3/agentrecall/verification-before-completion"><img src="https://agentmods.dev/badge/skills/zszz3/agentrecall/verification-before-completion.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00402 |
| Opus 5 | $0.00015 | $0.00201 |
| Sonnet 5 | $0.00006 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
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 6d 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
Verification Before Completion
Core rule
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
Confidence, old results, a clean-looking diff, or another agent's report are not evidence.
Verification gate
Before saying that anything works:
- Identify the command or observation that proves the exact claim.
- Run the complete verification now, not from memory or an earlier turn.
- Read the full output, exit code, failure count, and warnings.
- Compare the evidence with the claim and the acceptance criteria.
- If it does not prove the claim, report the actual state and remaining gap.
- Only then state the successful result and cite the evidence.
Evidence by claim
| Claim | Required evidence |
|---|---|
| Tests pass | Fresh test output with zero failures |
| Build succeeds | Fresh build command with exit code 0 |
| Bug is fixed | Original reproduction or regression test now passes |
| UI behavior works | Runtime observation of the requested interaction |
| Ready to merge | Relevant tests, build, diff review, and repository checks |
| Requirement is complete | Each acceptance criterion mapped to evidence |
A narrow test proves only its narrow behavior. Typecheck is not a build; a build is not an interaction test; a screenshot is not proof of persistence or backend behavior.
Regression tests
For a new regression test, witness the red-green cycle. When practical, revert the fix temporarily, confirm the test fails, restore the fix, and confirm it passes.
Reporting
- State exactly which commands ran and their results.
- Separate verified facts from unverified assumptions.
- Mention skipped checks and why they were skipped.
- Do not use “should”, “probably”, or “looks fixed” as substitutes for evidence.
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.
- 6d ago First seen · 50 lines · 31 tokens per session scan A 2b3e8b0596f8
verification-before-completion is a skill published in the GitHub repository zszz3/AgentRecall (762 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 402 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…