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 tahirraufkeeyu/software-development-agent-stack--sdas --skill changeloggit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/changelog)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/changelog"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/changelog/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/tahirraufkeeyu/software-development-agent-stack--sdas/changelog"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/changelog.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 | $0.00043 | $0.01947 |
| Opus 5 | $0.00022 | $0.00974 |
| Sonnet 5 | $0.00009 | $0.00389 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
changelog 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 10d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger this skill when:
- A release (tag, version bump, deploy) needs user-facing release notes.
- A monthly or quarterly "what shipped" digest is needed for customers, a newsletter, or a developer blog.
- A CHANGELOG.md file needs an update before a merge to main.
Do not use this skill for:
- Internal engineering rollups (use
status-updateinstead). - Security advisories — those follow a separate disclosure process.
- Commit-level audit logs — use
git logdirectly.
Inputs
Required:
- Repository (local path or GitHub URL).
- Version range — either two tags (
v2.3.0..v2.4.0) or two dates (2026-03-01..2026-03-31) or a single tag to compare against the previous tag. - Target version (the version being released, e.g.,
v2.4.0).
Optional:
- Audience —
customer(default),developer, orinternal. Affects filtering and tone. - Path to existing CHANGELOG.md — the skill will prepend the new section rather than overwrite.
- PR label filters — if the repo uses labels like
user-facingorchangelog:skip, use them.
Outputs
A Markdown block in Keep a Changelog format, grouped by the following categories (in order):
- Added — new features.
- Changed — changes to existing functionality.
- Deprecated — features marked for removal.
- Removed — features removed in this release.
- Fixed — bug fixes.
- Security — security-impacting changes.
Each bullet is a single sentence describing user impact, not the implementation. Ticket and PR numbers may be suffixed in parentheses.
Tool dependencies
- Bash —
git log,git tag,git diff --statfor scoping. - GitHub MCP (strongly recommended) —
list_pull_requeststo pull titles, bodies, labels, and merge status. - Read / Grep — to parse existing CHANGELOG.md and detect the previous version.
Procedure
- Resolve version range. If the user gave two tags, use them. If one tag, find the previous tag via
git describe --tags --abbrev=0 <tag>^. If dates, use--sinceand--until. - List merged PRs in range. Prefer GitHub MCP for metadata. For each PR: number, title, body, author, labels.
- Filter out non-user-facing PRs. Drop PRs that are:
- Labeled
changelog:skip,internal,chore,ci,test,refactor, ordocs:internal. - Titled with conventional-commit prefixes
chore:,ci:,test:,refactor:,build:,style:(unless the body explicitly says "user-facing"). - Touching only files under
.github/,ci/,tests/,docs/internal/.
- Labeled
- Categorize remaining PRs. Use both labels and conventional-commit prefixes:
feat:or labelfeature→ Added.fix:or labelbug→ Fixed.perf:→ Changed (with "Improved" phrasing) unless body says "fixes regression," then Fixed.security:or labelsecurity→ Security.deprecate:orremove:or labelbreaking→ Deprecated or Removed (read the body to decide).- Title starts with "Change X to Y" / "Update" → Changed.
- Translate to user impact. For each PR, rewrite the title into a user-facing sentence. Examples:
feat(auth): add refresh token rotation→ "Refresh tokens now rotate every 15 minutes, reducing the window in which a leaked token can be used."fix(billing): off-by-one in proration calculation→ "Fixed a rounding error in mid-cycle plan changes that occasionally charged $0.01 more than expected."perf(api): memoize feature flag lookups→ "Reduced p99 API latency by ~40ms for accounts with many feature flags."
- Deduplicate. Multiple PRs that ship the same feature should collapse into one bullet.
- Order within each section. Most user-impactful first. If the PR body includes an
Impact:field, use it to rank. - Write the version header.
## [<version>] - <YYYY-MM-DD>. If this is the first release for the project, title the section## [Unreleased]and let a human promote it at release time. - Prepend to existing CHANGELOG.md if one was provided. Do not overwrite.
- Return the draft. Recommend a 5-minute skim by a PM or DevRel before publishing.
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.
- 10d ago First seen · 140 lines · 43 tokens per session scan A 7db28b73eb82
changelog is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,947 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
updater_guide
Guidance for checking for and installing Row-Bot updates.