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 stark-ai-de/agent-skills --skill change-impactgit clone --depth 1 https://github.com/stark-ai-de/agent-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/stark-ai-de/agent-skills/change-impact)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/change-impact"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/change-impact/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/stark-ai-de/agent-skills/change-impact"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/change-impact.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 | $0.00062 | $0.01343 |
| Opus 5.5 | $0.00025 | $0.00537 |
| Sonnet 5.5 | $0.00012 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
change-impact 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 15d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Impact
Goal
Find concrete follow-up work a behavior change left behind, including unchanged artifacts with no symbol dependency on the modified implementation. Jev orders investigation; the host owns source interpretation and confirmation.
When to use
Select this skill during implementation or review when a public behavior, unit, default, scope, boundary, or user-visible promise changes. Automatic selection is enabled. Choose the applicable workflow from the task and proceed:
| Workflow | Use when | First action |
|---|---|---|
| Setup and connection check | Configure or diagnose this skill's Jev connection | Read setup; run doctor |
| Investigate a change | Find forgotten follow-up work in a known diff | Derive contracts and collect scoped source |
| Continue or report | Resume a saved investigation or summarize its findings | Revalidate saved data and get the next queue/report |
On a bare invocation with no identifiable task or saved review, ask which of these three workflows is intended. Do not introduce a selection question when existing context already identifies the requested outcome.
When not to use
Skip formatting, mechanical renames, and broad architectural audits. Use ordinary structural tooling for callers and imports. Tiny changes with no repeated behavior can be inspected directly. There is no demonstrated general accuracy or cost advantage over a capable host-only review; avoid unnecessary API work.
Inputs to inspect
Inspect the user's task, exact base/current revisions, owning boundaries, repository instructions, and before/after source. Use existing project authority for sending the selected text to TypeSafe. Credential presence alone does not grant that authority. Restrict the scope before collection.
What ships with it
9 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.
- agents/openai.yaml 262 B
- references/finding-criteria.md 1.7 KB
- references/helper-contract.md 9.0 KB
- references/setup.md 3.2 KB
- scripts/change-impact.mjs 5.5 KB runs code
- scripts/collect.mjs 12 KB runs code
- scripts/credentials.mjs 1.2 KB runs code
- scripts/rank.mjs 14 KB runs code
- scripts/review.mjs 7.0 KB runs code
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.
- 15d ago First seen · 129 lines · 62 tokens per session scan A aa5ab6f679f7
change-impact is a skill published in the GitHub repository stark-ai-de/agent-skills (8 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,343 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
muse-delegate
Delegate a coding task to Muse Code (muse) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Muse — phrasings like "have Muse do X", "delegate this to Muse", "run it through Muse", or "use Muse to implement/fix/refactor" — or wants…
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-review-changes
Review code changes using OpenLore risk, call, coverage, and cluster evidence without editing code. Use when asked for a change review, pre-PR safety check, or merge recommendation.
architect-init
Use when bootstrapping architecture documentation for a brownfield project by reverse-engineering ADRs from an existing codebase.
architect-analyze
Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or periodically to detect ADR↔AD drift, completeness gaps, and quality issues.
factory-review
Use when reviewing PRs for severity-ranked policy compliance against REVIEW.md, babysitting agent PRs to merge, or self-healing Important findings before a human sees them.