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 lossless-group/lossless-agent-skills --skill changelog-conventionsgit clone --depth 1 https://github.com/lossless-group/lossless-agent-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/lossless-group/lossless-agent-skills/changelog-conventions)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/changelog-conventions"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/changelog-conventions/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/lossless-group/lossless-agent-skills/changelog-conventions"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/changelog-conventions.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 | $0.00191 | $0.06868 |
| Opus 5 | $0.00096 | $0.03434 |
| Sonnet 5 | $0.00038 | $0.01374 |
| Haiku 4.5 | $0.00019 | $0.00687 |
Grade A, and why
changelog-conventions 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 12d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changelog Conventions
The single most important rule: it exists. Everything else is refinement.
Every Lossless repo at every level (project, true monorepo, pseudomonorepo) should have a changelog/ directory at the root, parallel to context-v/. Entries are written when meaningful chunks of work ship — or at least when they push.
Changelog First Development is a working Lossless theory: a fast-moving, meaningful changelog signals momentum to clients, audiences, contributors, and your own future self. The bus is leaving. The cruise ship is full. See references/changelog-first-development.md.
When to use this skill
- You just shipped or pushed a coherent chunk of work
- The user drops screenshots for an entry, or the work being logged is visual enough that prose alone undersells it (compose with [[prep-images-for-embed]])
- The user says "log this", "write a changelog", "ship note", "publish update"
- Scaffolding a new repo's
changelog/directory - Reviewing or updating an existing changelog entry
- Authoring a product release message (see
releases/subfolder below)
When to write an entry
Yes:
- A coherent chunk of work shipped (deployed, merged, released)
- Or at least pushed to a remote where someone else might land on it
- A new convention, blueprint, or tool became available
- Multiple smaller changes have accumulated into something worth announcing
Not necessarily:
- Every commit (most aren't worth a changelog)
- Typo fixes, minor refactors, work-in-progress
Future direction: the team is open to a "tweet-style" subset — short, frequent micro-changelogs for the in-between work that doesn't merit a full entry. Not implemented yet; flagged as a candidate.
Where it lives
<any-repo>/
├── context-v/ # living documentation
└── changelog/ # ← this skill governs this directory
├── YYYY-MM-DD_NN.md # entries
├── YYYY-MM-DD_NN.md
└── releases/ # for product-style projects only
├── v1.0.0.md
└── v1.1.0.md
What ships with it
7 files 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.
- 12d ago First seen · 351 lines · 191 tokens per session scan A bd3d1f5f2d00
changelog-conventions is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 19d ago), licensed MIT. It adds 191 tokens to every session and 6,868 once invoked, about $0.0010 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
version
Lock bundles with semantic versioning. Guides through version selection, updates files, and integrates with git.
gsd-complete-milestone
Archive completed milestone and prepare for next version.
utility-pm-release-conductor
Walk the guided 6-gate release runbook (G0 readiness, G1 adversarial review, G2 version bump and CHANGELOG, G2.5 commit and re-verify, G3 tag and push, G4 post-tag hygiene) via the pm-release-conductor sub-agent. Refuses gate bypasses and tags only the re-verified SHA. Use when cutting a pm-skills release.
release-finalizer
Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.
release-prep
Orchestrates the full release preparation flow for a plugin — version sync across 7+ files, bilingual release notes creation, and commit message drafting. Use before submitting a PR. Does NOT push or create a PR; that is handled by pr-submitter.
utility-pm-changelog-curator
Draft CHANGELOG entries from git log via the pm-changelog-curator sub-agent, applying the repo hygiene rules (describe what changed, public paths only, no attribution trailers). Returns a layered draft with a status summary for maintainer review; refuses a dirty working tree unless --committed-only is passed. Use when…