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/ao92265/claude-code-playbook/verification-before-completionnpx skills add ao92265/claude-code-playbook --skill verification-before-completiongit clone --depth 1 https://github.com/ao92265/claude-code-playbookWrote 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/ao92265/claude-code-playbook/verification-before-completion)<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/verification-before-completion"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/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 | $0.00101 | $0.01268 |
| Opus 5 | $0.00051 | $0.00634 |
| Sonnet 5 | $0.00020 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
verification-before-completion scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| "Deployed" | Health check or status endpoint (e.g., `curl https://api/health`) | How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Core Rule: NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE.
Step 1: Identify the Proof Command
Before claiming any work is complete, determine the exact command that proves the claim:
| Claim type | Required proof command |
|---|---|
| "Tests pass" | Fresh test runner invocation (e.g., pytest, npm test) |
| "Bug fixed" | Test that reproduces the bug, run after the fix |
| "Deployed" | Health check or status endpoint (e.g., curl https://api/health) |
| "Configured" | Command that reads back the configured value |
| "Build succeeds" | Full build command (e.g., tsc --noEmit, npm run build) |
| "Complete" | All acceptance criteria individually verified |
If no proof command can be identified, do not proceed to a completion claim. Ask the user how to verify.
Step 2: Scan Own Response for Unverified Language
Before finalizing any response that implies completion, check for the following phrases. If any are present, they must be replaced with verified evidence or removed:
| Flagged phrase | Problem |
|---|---|
| "should work now" | Conditional, not verified |
| "that should fix it" | Assumption, not proof |
| "probably passes" | Uncertainty — not verified |
| "looks good" | Visual inspection is not execution |
| "Done!" (before testing) | Premature |
| "I believe this works" | Belief is not evidence |
If any flagged phrase is found: do not publish the response. Execute Step 3 first.
Rationalization Prevention
If you catch yourself thinking any of these, STOP and run verification instead:
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler ≠ tests |
| "Agent said success" | Verify independently — agent reports are claims, not proof |
| "Partial check is enough" | Partial proves nothing about the whole |
| "Different words so rule doesn't apply" | Spirit over letter — any implication of success counts |
| "I'll verify after I commit" | Verification gates the commit, not the other way around |
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 · 138 lines · 101 tokens per session scan A 2a5aa2544339
verification-before-completion is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 20d ago), licensed MIT. It adds 101 tokens to every session and 1,268 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.