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 MadAppGang/magus --skill verification-before-completiongit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/verification-before-completion)<a href="https://agentmods.dev/skills/madappgang/magus/verification-before-completion"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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 | $0.00047 | $0.01693 |
| Opus 5 | $0.00023 | $0.00847 |
| Sonnet 5 | $0.00009 | $0.00339 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade B, and why
verification-before-completion scanned grade B with 2 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 4d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
$ curl -X POST http://localhost:8000/users -d '{"email":"invalid"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| API changes | API test output or curl result | `curl -X POST ...` | This is a copy
91% identical to verification-before-completion — 9 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Iron Law: "NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE"
When to Use
This skill applies whenever you:
- Mark a todo item as complete
- Claim a bug is fixed
- Report a feature is ready
- State implementation is done
- Close a task or issue
- Prepare to commit changes
Red Flags (Violation Indicators)
- "should be done" / "should work now" (assumed completion)
- "probably works" / "likely fixed" (uncertainty without verification)
- "seems to work" / "appears correct" (observation without test)
- "Great!" / "Perfect!" / "All set!" (celebration without evidence)
- "I already tested this earlier" (stale evidence)
- Completion claim without test output shown
- Completion claim without grep verification for file changes
- Completion claim without screenshot for UI changes
- Completion claim without git diff for code changes
- Completion claim without build logs for configuration changes
- Completion claim without CI link for deployment changes
- "Just a small change, no need to verify" (size-based rationalization)
Key Concepts
Fresh Verification Principle
Verification must be fresh (performed after the claimed change) and explicit (evidence shown, not described).
Wrong:
Fixed the login bug in auth.ts. Should be working now.
Correct:
Fixed the login bug in auth.ts line 42:
git diff src/auth.ts:
- if (user.token == null) {
+ if (user.token === undefined || user.token === null) {
Test output:
✓ should reject undefined token (15ms)
✓ should reject null token (12ms)
✓ should accept valid token (8ms)
Evidence Types by Change Type
| Change Type | Required Evidence | Tool/Method |
|---|---|---|
| Logic/algorithm | Test output showing pass | bun test, pytest, go test |
| File creation | Grep verification or ls output | grep -r "pattern" . or ls -la path/ |
| UI/styling | Screenshot or video | Browser DevTools screenshot |
| Configuration | Build logs showing success | npm run build, cargo build |
| Deployment | CI link or deployment logs | GitHub Actions URL, kubectl logs |
| API changes | API test output or curl result | curl -X POST ... |
| Data migration | Row count or sample query | SELECT COUNT(*) FROM ... |
| Performance fix | Benchmark comparison (before/after) | hyperfine, go test -bench |
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.
- 4d ago First seen · 228 lines · 47 tokens per session scan B 4bd7b5c401b9
verification-before-completion is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,693 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 91% identical to verification-before-completion, differing in 9 lines, and is treated as a copy.
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.