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 yarlson/yarstack --skill changes-reportgit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/changes-report)<a href="https://agentmods.dev/skills/yarlson/yarstack/changes-report"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/changes-report/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/yarlson/yarstack/changes-report"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/changes-report.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 | $0.00054 | $0.01083 |
| Opus 5.5 | $0.00022 | $0.00433 |
| Sonnet 5.5 | $0.00011 | $0.00217 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
changes-report 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Changes for a Period
Produce one evidence-based account of what changed and why it matters, independent of commit and pull request boundaries.
Required Input
Require a date or period. Accept a single YYYY-MM-DD date, an explicit start and end date, or a clear relative period such as today, this week, or last week. If the user did not specify one, ask which date or period to report and stop. If it cannot be resolved to exact bounds, ask for a precise date or period and stop.
Use the local system timezone unless the user specifies another timezone. Treat a single date as the half-open period from 00:00 on that date to 00:00 on the next date. Treat an explicit end date as inclusive by ending at 00:00 on the following date. Resolve calendar weeks from Monday at 00:00. End a relative period that includes the present, such as today or this week, at the current time; use full calendar bounds for completed periods such as yesterday or last week.
Before inspecting changes, record the resolved start, exclusive end, timezone, and human-readable period label. Use those exact bounds throughout the report.
Workflow
- Confirm the repository and target branch. Use the current repository and branch when the user does not name them. Fetch and read the remote-tracking branch, such as
origin/main, because the local branch can be behind. If you cannot fetch, use the local branch and report the time of its last update as a limit. - List the merge, squash, and direct commits that entered the target branch during the period with
git log --first-parent --since=<start> --until=<end> --format='%H %cI %s' <branch>. Find the branch state before the period withgit rev-list -1 --first-parent --before=<start> <branch>, and read the net change from that state to the last in-period commit. Then read individual diffs, full changed files, tests, configuration, and surrounding code as needed. First-parent history counts each merge once, with its constituent commits inside it.
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 Changed · +2 lines ad31ee17c03e
- 1mo ago First seen · 57 lines · 54 tokens per session scan A fa88ae0bd566
changes-report is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 1,083 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 2026-08-31.
Other skills, from other repositories
owndiff-pre-commit
Audit OwnDiff changes before committing or releasing by checking scope, generated artifacts, private data, documentation accuracy, version consistency, structured files, tests, and the OwnDiff ownership gate. Use when a user asks to verify, clean up, prepare, commit, publish, or release changes in the OwnDiff…
git-review
Review a repository diff for accidental changes, secrets, generated files, dependency and migration impact, tests, documentation, and scope before completion.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.