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 tony/skills --skill refreshgit clone --depth 1 https://github.com/tony/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/tony/skills/refresh)<a href="https://agentmods.dev/skills/tony/skills/refresh"><img src="https://agentmods.dev/badge/skills/tony/skills/refresh/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/tony/skills/refresh"><img src="https://agentmods.dev/badge/skills/tony/skills/refresh.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 | $0.00022 | $0.01663 |
| Opus 5.5 | $0.00009 | $0.00665 |
| Sonnet 5.5 | $0.00004 | $0.00333 |
| Haiku 4.5 | $0.00002 | $0.00166 |
Grade A, and why
refresh 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 8d 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.
This is a copy
89% identical to changelog-refresh — 37 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Changelog Entries
Bring the changelog entries this branch introduced back in sync with what the
branch does now. With --commit, the correction lands as a new commit on top;
otherwise the edit stays uncommitted for the user to commit. History is never
rewritten; /changelog:rewrite-aggressively does that.
Scope: edit only changelog content the branch added. Entries from the base branch, whether earlier releases or other work's unreleased entries, are read-only. A correction that needs a line the branch did not add: ask, or without a question tool leave it and note the limitation.
Additional context from user: $ARGUMENTS
Read these first:
../../references/branch-scope.md: a branch is not a release, base branch, changelog file lookup, whole-branch perspective.../../references/entry-rules.md: categorizing, format, voice, exclusions.../../references/commit-message.md: used in Phase 4.
Write entries, commit messages, and user-facing replies per
../../references/prose-rules.md.
Phase 1: Establish scope
-
Detect the base and find the changelog file per
branch-scope.md. No changelog changes on this branch and no changelog file: suggest/changelog:changelogand stop. -
Extract the branch's changelog footprint. The added lines are the branch-owned entries, the only region this skill may edit:
$ git diff origin/<base>...HEAD -- <changelog-file> -
List the branch commits that touch the file (with no
originremote, substitute the local base name fororigin/<base>in these commands):$ git log origin/<base>..HEAD --oneline -- <changelog-file>None: say so and offer the
/changelog:changelogprocedure instead. -
Check the changelog is clean per
commit-message.md; when it is not, edit only and say why.
Phase 2: Recompute what the entries should say
Apply branch-scope.md and entry-rules.md: read conventions, categorize, and
generate the entries the branch should have from its current net change
(git log origin/<base>..HEAD and git diff origin/<base>...HEAD, three-dot,
so base commits the fetch pulled in stay out). For the PR number, run
gh pr view --json number --jq .number; on failure write (#???). Never copy
a number from a dropped or stale entry.
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.
- 8d ago Changed · +28 lines 03717861e9d6
- 1mo ago First seen · 128 lines · 22 tokens per session scan A 652af6c61f34
refresh is a skill published in the GitHub repository tony/skills (0 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 1,663 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to changelog-refresh, differing in 37 lines, and is treated as a copy.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.