release-debrief

A release-notes summary tool for Claude Code, OpenCode, llama-swap, and llama.cpp that compares the latest release with the last summary seen.

In plain words
What is it for?
Use it when you want a concise update on what changed in one of those supported developer tools.
Why use it?
It shows only the changes since the previous review, reducing the need to read an entire changelog again.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sammcj/agentic-coding/release-debrief
Any agent
npx skills add sammcj/agentic-coding --skill release-debrief
Clone the repo
git clone --depth 1 https://github.com/sammcj/agentic-coding

Made for: Claude Code, Codex.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00064 $0.01711
Opus 5 $0.00032 $0.00856
Sonnet 5 $0.00013 $0.00342
Haiku 4.5 $0.00006 $0.00171

Measured 3d ago against content hash 1b0cb4e4692a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-debrief 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 3d 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.

Skills/release-debrief/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Notes Catch-Up

Summarise what's changed in a supported tool since the user last ran this skill against it. No walkthroughs, no exercises. Focused digest of the delta.

Supported Tools

Each tool has a profile in resources/tools/<tool>.md (source URLs, buckets, gotchas) and an output file in resources/outputs/<tool>.md (last-seen version and summary history). Resolve both paths relative to this SKILL.md, not the user's current working directory.

Tool Aliases the user may type Profile Output
Claude Code claude-code, claudecode, cc resources/tools/claude-code.md resources/outputs/claude-code.md
OpenCode opencode, open-code resources/tools/opencode.md resources/outputs/opencode.md
llama-swap llama-swap, llamaswap resources/tools/llama-swap.md resources/outputs/llama-swap.md
llama.cpp llama-cpp, llama.cpp, llamacpp resources/tools/llama-cpp.md resources/outputs/llama-cpp.md

Tool selection: match the tool from the user's prompt against the aliases above. If the user names something not in this table, reply with the supported list and stop.

Flow

  1. Load the tool profile. Read resources/tools/<tool>.md. It tells you where to fetch the changelog, how the version scheme works, which buckets to group under, what to drop, and what to watch out for. Treat the profile as authoritative for that tool.

  2. Read state. Load the tool's output file. Parse last_seen_version from the frontmatter. If the file is missing, empty, or has no frontmatter version, treat as a first run: summarise the last 3 releases per the profile's version scheme, without prompting.

  3. Fetch the current changelog. Use WebFetch or ctx_fetch_and_index against the profile's Primary source. Pull Supporting sources only when you need context for an entry (config schema comparison, API doc linking, editorial summary for colour). When the profile lists Conditional sources, test each condition against the delta once you have it and fetch the ones that hold - those carry buckets of their own.

Read the full file on GitHub · 113 lines

Files

What ships with it

5 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.

Changes

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.

  1. 3d ago First seen · 113 lines · 64 tokens per session scan A 1b0cb4e4692a

Subscribe to this mod's changes

release-debrief is a skill published in the GitHub repository sammcj/agentic-coding (158 stars, last pushed 8d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,711 once invoked, about $0.0003 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.