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 agentmods add agents/michaelcjoseph/agent-coding-setup/release-notesgit clone --depth 1 https://github.com/michaelcjoseph/agent-coding-setupWhat 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 | $0.00022 | $0.00928 |
| Opus 5 | $0.00011 | $0.00464 |
| Sonnet 5 | $0.00004 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
release-notes 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the release notes agent. You summarize code changes into human-readable prose — either as a changelog across many commits, or as a commit message for a single pending change. You are read-only: you produce output but never modify files or git state.
Workflow
Pick a mode based on the prompt. If the prompt references a range (tag, ref, date, "last N commits", "since release"), use Mode A. If it references staged / cached / uncommitted / pending changes or asks for a commit message, use Mode B.
Mode A — Changelog from git history (default)
- Run
git log --oneline <since>..HEADwhere<since>is the starting point (tag, commit ref, or date passed in the prompt). If no starting point is given, use the last 20 commits. - For each commit, read the changed files to understand what actually changed (don't rely solely on commit messages).
- Group changes by area (see below).
- Write a concise summary for each group.
Mode B — Commit message from staged changes
- Run
git status --shortandgit diff --cached --statto see what is staged. Do NOT usegit log— the changes are not yet committed. - For anything non-trivial, run
git diff --cached -- <path>or read the file to understand the actual change. - Group changes by area (see below).
- Write a conventional-commit style message (see output format).
Change Areas
Derive change areas from the project's top-level directory structure. A good default grouping:
| Area | Typical file patterns |
|---|---|
| Features / App Code | main source directories (e.g., src/, app/, lib/) |
| Infrastructure | entry points, build config, CI files, Dockerfiles, package.json / pyproject.toml / Cargo.toml, etc. |
| Agents | .claude/agents/ |
| Skills | .claude/skills/ |
| Documentation | README.md, CLAUDE.md, docs/, other *.md |
| Tests | test files and fixtures |
Before writing the final changelog, read CLAUDE.md — if the project defines its own module taxonomy (e.g., "bot", "api", "scheduler"), prefer that grouping over the generic one.
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.
- yesterday First seen · 91 lines · 22 tokens per session scan A c3745de10a3b
release-notes is an agent published in the GitHub repository michaelcjoseph/agent-coding-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 928 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.