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 oleg494/coding-kit --skill verification-before-completiongit clone --depth 1 https://github.com/oleg494/coding-kitWrote 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/oleg494/coding-kit/verification-before-completion)<a href="https://agentmods.dev/skills/oleg494/coding-kit/verification-before-completion"><img src="https://agentmods.dev/badge/skills/oleg494/coding-kit/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/oleg494/coding-kit/verification-before-completion"><img src="https://agentmods.dev/badge/skills/oleg494/coding-kit/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 | $0.00057 | $0.01277 |
| Opus 5.5 | $0.00023 | $0.00511 |
| Sonnet 5.5 | $0.00011 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00128 |
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 2d 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.
This is a copy
92% identical to verification-before-completion — 77 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Overview
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
The Iron Law
NO COMPLETION CLAIMS WITHOUT APPLICABLE VERIFICATION EVIDENCE
"Applicable" means evidence valid for the current checked state: revision/snapshot, exact command, scope, environment, run timestamp. Reuse existing evidence until an invalidation condition occurs (code change, failure, or unresolved concern) and report that provenance instead of treating the chat turn as a clock; a fresh invocation is required only when no valid evidence for the checked state exists.
The Gate Function
BEFORE claiming a verified result:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute that command completely when no applicable evidence exists
for the current checked state — "complete" means no truncated or partial
run of the check that proves THIS claim, not every check the repo has
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence
5. ONLY THEN: Make the claim
Skip any step = lying, not verifying. Reusing evidence that is still valid
for the checked state (same revision, no invalidating change/failure/concern)
is not skipping — but claiming without either is lying.
Scope is part of honesty, in both directions. Claiming a suite-wide green you did not run is a lie; re-running an unchanged check with no new changes, failures, or unresolved concerns is ceremony, not verification. Broaden when scope warrants: shared code touched, or a failure the targeted check exposed.
Common Failures
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Test command output: 0 failures on checked state | Unchecked assumption, "should pass" |
| Linter clean | Linter output: 0 errors | Extrapolating to the claim's scope; a different check's output for that scope |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | Inspect changed artifacts and exercise the claimed behavior | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |
What ships with it
1 file 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.
- 2d ago Changed bdb7ba88e50d
- 8d ago Changed · +14 tokens per session 2fd2bb583533
- 11d ago Changed · +7 lines 0b1686673079
- 25d ago Changed cd0522e10844
- 26d ago Changed 015a17fe4c87
- 1mo ago Changed 41e0df25361b
- 1mo ago Changed · -8 lines 2ad90a849d45
- 1mo ago Changed 32b352e60348
- 1mo ago Changed · +6 lines f644a01b4433
- 1mo ago First seen · 135 lines · 43 tokens per session scan A 311af2755fab
verification-before-completion is a skill published in the GitHub repository oleg494/coding-kit (3 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,277 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to verification-before-completion, differing in 77 lines, and is treated as a copy.
Other skills, from other repositories
agentic-evals
Design evaluation contracts and test plans for agentic systems. Create deterministic tests, trajectory evals, quality dimensions, gold-set criteria, and CI gates before or after implementation. Use when asked for tests first, an eval plan, success criteria, non-deterministic testing, LLM-as-judge setup, or…
spae-check
Per-task verification gate for SPAE. Compares active task Intent, Acceptance, and Verification against repo evidence; routes gaps to /fix or advances a clear task.
spae-verify
Arbiter for the SPAE framework. Compares implementation against SPEC.md and determines workstream completion.
spae-spawn
Executes the build phase of the SPAE structured workflow autonomously, cycling build, check, and fix per task.
coverage
Orchestrates test agents sequentially to cover behavioral gaps.
writing-livekit-scenarios
Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them. Use when the user asks "what should I test", "generate simulation scenarios", "write scenarios for my agent", "add a scenario for X", "organize my scenario files", "my simulations are flaky", "the scenario hits my…