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 ckorhonen/swe-skills --skill change-validation-plannergit clone --depth 1 https://github.com/ckorhonen/swe-skillsWrote 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/ckorhonen/swe-skills/change-validation-planner)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/change-validation-planner"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/change-validation-planner/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/ckorhonen/swe-skills/change-validation-planner"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/change-validation-planner.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 | $0.00086 | $0.01263 |
| Opus 5 | $0.00043 | $0.00632 |
| Sonnet 5 | $0.00017 | $0.00253 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
swe:change-validation-planner 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 10d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Change Validation Planner
What This Skill Does
Use this skill to turn a scoped code change into a disciplined validation plan.
The job is not to debug the change or rewrite tests. The job is to decide:
- what evidence is already enough
- what to validate first
- what to validate only if the earlier checks fail or remain ambiguous
- what remains unverified even after the recommended checks
The result should help an engineer or agent validate a change without wasting time on broad, low-signal commands.
When To Use
Use this skill when the user wants to:
- know what to run before merging a scoped change
- validate a diff, PR, or local edit with the smallest trustworthy command set
- compare narrow versus broad validation options
- understand what a change still does not prove
- plan a repeatable validation sequence for a specific repository surface
Do Not Use
Do not use this skill for:
- implementing the code change itself
- writing or expanding tests as the primary task
- generic QA across the whole repo with no scoped change
- root-cause debugging when the failure cause is still unknown
- architecture planning or release orchestration
Inputs To Confirm
Confirm or infer:
- the exact change scope, diff, or PR
- which files, packages, or services are touched
- what commands already exist in the repo
- whether the user wants a quick plan or a deeper validation ladder
- any flaky suites, slow commands, or no-touch areas
- whether CI signals are available for the changed surface
If the scope is missing, ask for the smallest additional detail needed to bound the validation plan.
Tooling Stance
This skill is tool agnostic.
Prefer the repository's own validation entry points first, such as:
- targeted tests for the touched module or package
- lint or typecheck commands that cover the affected surface
- build or compile checks when the change crosses a boundary
- integration or e2e checks only when the change reaches those seams
Do not jump directly to the slowest or broadest suite unless the change is actually system-wide or earlier checks are not meaningful.
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.
- 10d ago First seen · 194 lines · 86 tokens per session scan A 7592bcb1132a
swe:change-validation-planner is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,263 once invoked, about $0.0004 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
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
test-gen
Generate and verify tests — happy path, edge cases, error paths — using the project's own framework and patterns.
meta-skill-tester
A testing tool for checking the quality of coding-agent skills. It compares results with and without a skill, runs regression and chain tests, measures usage and time, and produces a scored report.
verify
Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown.
autoresearch
Autonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation modes — deterministic (eval.py with proxy heuristics) or AI judge (LLM rubric scoring). Uses four-way separation in both modes. Inspired by Karpathy's autoresearch.