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/slowdini/slow-powers/verifying-development-worknpx skills add slowdini/slow-powers --skill verifying-development-workgit clone --depth 1 https://github.com/slowdini/slow-powersWrote 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/slowdini/slow-powers/verifying-development-work)<a href="https://agentmods.dev/skills/slowdini/slow-powers/verifying-development-work"><img src="https://agentmods.dev/badge/skills/slowdini/slow-powers/verifying-development-work.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 | $0.00028 | $0.02162 |
| Opus 5 | $0.00014 | $0.01081 |
| Sonnet 5 | $0.00006 | $0.00432 |
| Haiku 4.5 | $0.00003 | $0.00216 |
Grade A, and why
verifying-development-work 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying development work
Claiming work is complete without verification is an assumption, not a fact. Handing work back without a review pass is a guess that the diff is the right diff. Finishing requires both: verification proves the code runs; review proves it's the right code.
THE IRON LAW: NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. NO HANDOFF WITHOUT A REVIEW PASS OVER THE DIFF.
Violating the letter of the rules is violating the spirit of the rules.
Finish: review, verify, then hand off
When you believe the work itself is done, run these finishing phases in order. Review comes first so any fixes happen before the evidence you hand back; verification comes next so the claim covers the returned code; integration choices come last because they belong to the user.
- Review and fix the diff — follow the code-review reference, including its comment-hygiene checks. Review catches what running can't: silent regressions, missed edge cases, leftover debug code, noisy comments, reuse or simplification. Fix or flag each finding. Once behavior-changing fixes are done, the code is frozen. A small diff never exempts this phase: review depth is sized inside the reference ("Size the review to the change") — a small change means a small review, never no review.
- Establish final verification evidence — apply the Gate Function (below) to the frozen code. If you already have qualifying current-session evidence and the review made no behavior-changing edits after it, reuse it and present that output. Otherwise run the command fresh and present that output.
- Surface integration options — state that the work is reviewed and verified, then offer the user choices such as merge, push/open PR, leave as-is, or discard. Do not choose for them.
Copy this checklist into your task tracker the moment you start finishing, and tick each box in order. The ordering is the discipline — and an untracked checklist is one whose middle steps get skipped under momentum:
What ships with it
41 files 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.
- evals/baseline/BASELINE.md 897 B
- evals/baseline/benchmark.json 1.2 KB
- evals/baseline/grading/build-implied-by-edit__new_skill.json 1.8 KB
- evals/baseline/grading/build-implied-by-edit__old_skill.json 1.8 KB
- evals/baseline/grading/claim-without-running__new_skill.json 1.8 KB
- evals/baseline/grading/claim-without-running__old_skill.json 2.0 KB
- evals/baseline/grading/comment-hygiene-at-handoff__new_skill.json 3.3 KB
- evals/baseline/grading/comment-hygiene-at-handoff__old_skill.json 2.8 KB
- evals/baseline/grading/reuse-fresh-primary-verification__new_skill.json 2.2 KB
- evals/baseline/grading/reuse-fresh-primary-verification__old_skill.json 2.2 KB
- evals/baseline/grading/seeded-done-tests-pass-ship-it__new_skill.json 1.8 KB
- evals/baseline/grading/seeded-done-tests-pass-ship-it__old_skill.json 2.0 KB
- evals/baseline/grading/seeded-grown-long-file__new_skill.json 2.7 KB
- evals/baseline/grading/seeded-grown-long-file__old_skill.json 2.3 KB
- evals/baseline/grading/seeded-small-change-review-skip__new_skill.json 2.4 KB
- evals/baseline/grading/seeded-small-change-review-skip__old_skill.json 2.2 KB
- evals/baseline/grading/seeded-teammate-pasted-evidence__new_skill.json 2.4 KB
- evals/baseline/grading/seeded-teammate-pasted-evidence__old_skill.json 2.0 KB
- evals/baseline/grading/wrap-it-up-handoff__new_skill.json 2.9 KB
- evals/baseline/grading/wrap-it-up-handoff__old_skill.json 2.4 KB
- evals/baseline/NOTES.md 4.7 KB
- evals/evals.json 32 KB
- evals/fixtures/build-implied-by-edit/api.ts 35 B runs code
- evals/fixtures/build-implied-by-edit/consumer.ts 54 B runs code
- evals/fixtures/build-implied-by-edit/tsconfig.json 518 B
- evals/fixtures/claim-without-running/sum.test.ts 214 B runs code
- evals/fixtures/claim-without-running/sum.ts 52 B runs code
- evals/fixtures/comment-hygiene-at-handoff/slugify.test.ts 409 B runs code
- evals/fixtures/comment-hygiene-at-handoff/slugify.ts 1.0 KB runs code
- evals/fixtures/grown-long-file/field-validators.test.ts 1.3 KB runs code
- evals/fixtures/grown-long-file/field-validators.ts 14 KB runs code
- evals/fixtures/seeded-done-tests-pass-ship-it/pricing.test.ts 535 B runs code
- evals/fixtures/seeded-done-tests-pass-ship-it/pricing.ts 661 B runs code
- evals/fixtures/seeded-small-change-review-skip/clamp.test.ts 478 B runs code
- evals/fixtures/seeded-small-change-review-skip/clamp.ts 278 B runs code
- evals/fixtures/seeded-teammate-pasted-evidence/checkout.test.ts 716 B runs code
- evals/fixtures/seeded-teammate-pasted-evidence/checkout.ts 661 B runs code
- evals/fixtures/wrap-it-up-handoff/limiter.test.ts 691 B runs code
- evals/fixtures/wrap-it-up-handoff/limiter.ts 758 B runs code
- references/code-review.md 5.2 KB
- references/long-files.md 7.4 KB
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.
- 3d ago First seen · 121 lines · 28 tokens per session scan A 5e9208b2487f
verifying-development-work is a skill published in the GitHub repository slowdini/slow-powers (2 stars, last pushed 20d ago), licensed MIT. It adds 28 tokens to every session and 2,162 once invoked, about $0.0001 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
ospec-goal
Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
ts-sdk-author
Design, build, verify, and publish production-grade TypeScript SDKs as npm packages inside a pnpm monorepo. Covers workspace layout, public API and module boundaries, plugin extension points, branded types and library-tuned tsconfig, tsdown bundling (vs tsup/tsc-only/unbuild), package.json exports with dual ESM+CJS…
first-principles-thinking
Systematic first principles thinking for any problem domain. Use when the user says "analyze from first principles", "第一性原理", "从根本分析", "从零开始思考", "think from scratch", "question this design", "is this the right approach", "challenge assumptions", "挑战假设", "为什么要这样做", "有没有更好的方案", "why are we doing it this way", or needs…
python-design
Python design patterns for CLI scripts and utilities — type-first development, deep modules, complexity management, and red flags. Use when reading, writing, reviewing, or refactoring Python files, especially in .trellis/scripts/ or any CLI/scripting context. Also activate when planning module structure, deciding…