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 OutlineDriven/outline-driven-development --skill changelog-updatesgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/changelog-updates)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/changelog-updates"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/changelog-updates.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.00836 |
| Opus 5 | $0.00014 | $0.00418 |
| Sonnet 5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
changelog-updates 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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changelog updates
Contract
| Field | Bound contract |
|---|---|
| Trigger | A release or a since-tag window needs user-facing release communication drafted |
| Authority | Reversible local: writes only a draft release note and the file-based since-tag marker; rollback is version control. No remote mutation, no git tag, no publish, no release. |
| Side effect | Writes or updates one draft release note file and advances the since-tag state marker exactly once |
| Done | The draft covers exactly the since-tag window and the marker advanced once; publishing remains a separate human action |
Inputs
- A repository with a file-based since-tag state marker (a local file identifying the last covered release boundary). Required.
- The current head reference or commit range to cover. Required.
- The set of user-facing changes since the marker (commits, merged PRs, or issues). Required; gathered from local history only.
- An optional audience or tone preference (e.g., developer-facing, end-user-facing). Optional; defaults to developer-facing.
Procedure
- Read the since-tag state marker and record the boundary it names. Do not mutate it yet. Done when: the boundary is read and recorded.
- Compute the since-tag window as the range from that marker to the current head. If the marker is missing or ambiguous, stop and report the missing boundary. Done when: the window is computed from marker to head, or the missing boundary is reported.
- Gather user-facing changes inside the window from local history only: commit messages, merged PR titles, and linked issues. Classify each as Added, Changed, Fixed, Deprecated, Removed, or Security. Done when: every change in the window is gathered and classified.
- Compose a draft release note covering exactly the window: one section per non-empty category, one bullet per change, no entries outside the window, no forward-looking or invented items. Done when: the draft covers exactly the window with one section per non-empty category.
- Write or update the draft release note file at the project's changelog location. If the location is unspecified, write to a draft file adjacent to the marker and report the chosen path. Done when: the draft is written to the changelog location and the path is reported.
- Advance the file-based since-tag state marker exactly once to the current head so the next run starts from this boundary. Update the marker file contents to record the current head commit. Do not create a git tag, push, publish, or open a release. Done when: the marker file is advanced once to the current head.
- Report the draft path, the window covered, the change count per category, and that publishing is a separate human action. Done when: the report is delivered with draft path, window, counts, and publishing notice.
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.
- 2d ago Changed · -16 tokens per session f527ba2c80c6
- 4d ago First seen · 43 lines · 43 tokens per session scan A 9cc81d6c01b5
changelog-updates is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 836 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
git-branchless
Use when asked for multi-commit stack edits, rebases, fixups, or stacked-PR publishing with branchless git idioms. Not for plain-git workflows in repos without branchless.
atomic-issues-prs
Use when the user says "atomic PRs" or requests one issue or PR per logical change. Don't use for single-change pushes or uncommitted change-sets.
post-merge-cleanup
Use when a landed merge, release, or completed change needs its cleanup surface reconciled. Scans for stale TODOs, deprecations, unused flags, and doc gaps. Not for unrelated refactoring.
git-workflow-and-versioning
Use when the user asks for release, version bump, changelog, or branch workflow beyond a single commit. Don't use for single commits or for publishing to a package registry.
lockstep-version-guard
Use when a human invokes the release gate to prove all 28 ODIN plugins share one canonical version. Emits a per-file comparison and exits non-zero on mismatch. Don't use to edit release metadata or for remote, credential, publish, deploy, or irreversible changes.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.