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 starbringer/AI-Insights --skill ai-change-impactgit clone --depth 1 https://github.com/starbringer/AI-InsightsWrote 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/starbringer/ai-insights/ai-change-impact)<a href="https://agentmods.dev/skills/starbringer/ai-insights/ai-change-impact"><img src="https://agentmods.dev/badge/skills/starbringer/ai-insights/ai-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/starbringer/ai-insights/ai-change-impact"><img src="https://agentmods.dev/badge/skills/starbringer/ai-insights/ai-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 | $0.00169 | $0.01665 |
| Opus 5 | $0.00084 | $0.00833 |
| Sonnet 5 | $0.00034 | $0.00333 |
| Haiku 4.5 | $0.00017 | $0.00167 |
Grade A, and why
ai-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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI change impact
Answer one question: did that change save money, and how much?
Three rules govern the whole analysis:
- The arithmetic is the app's job, the judgement is yours.
compare_runsandcompare_periodsreturn an exact decomposition. Your value is deciding whether the comparison is fair and saying so plainly. - Report the caveats. Both tools return a
caveatsarray generated from the actual data. Never drop it. A saving the user cannot rely on is worse than no number, because they will act on it. - You never edit config here. This skill measures. If the answer is "it got worse", say that and stop; fixing it is a separate request.
1. Pick the mode
| The user has… | Mode | Tool |
|---|---|---|
| Two runs to compare (re-ran the same task) | Run vs run | compare_runs |
| Just kept working after the change | Period vs period | compare_periods |
| A change but no idea when | Find the split first | get_harness_changes |
Run mode is exact but n = 1. Period mode is noisier but reflects real use. When both are possible, do both: they answer different questions, and agreement between them is the strongest evidence you can offer.
2. Establish scope and horizon
Run list_providers, then pick the provider: the one the user named, the only one
with hasData: true, or ask. Pass it as provider on every call — a harness
diff needs a concrete provider and is skipped for "all".
Then check get_data_retention before asking for any window. Records older
than retentionDays are deleted, not hidden. If the "before" side predates
oldestRetainedTimestamp, say so directly:
Your retention is set to 30 days, so nothing before 2026-06-29 exists any more — that period cannot be compared. Raise the retention setting now if you want this question answerable next month; the data cannot be recovered once deleted.
Do not fall back to a window you can answer and present it as the answer.
3. Find the split point
What ships with it
1 file 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.
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.
- 11d ago First seen · 137 lines · 0 tokens per session scan A 890b2e849ecb
ai-change-impact is a skill published in the GitHub repository starbringer/AI-Insights (2 stars, last pushed 22d ago), licensed MIT. It adds 169 tokens to every session and 1,665 once invoked, about $0.0008 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
ci-self-heal
A diagnostic guide for analysing failed continuous-integration checks. Continuous integration, or CI, automatically tests and builds code changes; this guide classifies failures and suggests fixes without editing the code.
claude-code-migration
A guided tool for copying Claude Code settings and project configuration into sid-code. It checks what can be moved, asks before writing, and records what was transferred.
code-review
A review process for a pull request, which is a proposed set of code changes. It examines the changed code and its surrounding files for bugs, security problems, design issues, and lint errors.
security-audit
A security review skill for examining code changes in a pull request, which is a proposed set of changes awaiting approval. It reports issues such as injection, exposed secrets, unsafe authentication, weak cryptography, vulnerable dependencies, and infrastructure mistakes.
incident-rca
A diagnostic process for producing a structured root-cause analysis of a serious production incident, such as a P0 or P1 outage. It compares logs, measurements, request traces, code changes, and architecture decisions, and gives ranked explanations and actions.
code-governance
A review skill that checks pull-request changes for software licenses, personal information, compliance details, and an audit trail. An audit trail is a record showing what was checked and why.