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/ihudak/ihudak-claude-plugins/diff-summarizergit clone --depth 1 https://github.com/ihudak/ihudak-claude-pluginsWrote 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/agents/ihudak/ihudak-claude-plugins/diff-summarizer)<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/diff-summarizer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/diff-summarizer.svg" alt="Measured on agentmods" 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 | $0.00096 | $0.03588 |
| Opus 5 | $0.00048 | $0.01794 |
| Sonnet 5 | $0.00019 | $0.00718 |
| Haiku 4.5 | $0.00010 | $0.00359 |
Grade A, and why
diff-summarizer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- NEVER make HTTPS / REST calls to GitHub outside the `gh` CLI. No direct API calls, no raw `curl` to `api.github.com`. How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read ${CLAUDE_PLUGIN_ROOT}/references/handoff/diff-summarizer.md for the exact input/output document format.
Summarise a single code repository's PR diff(s) from a documentation-consumer's point of view. One instance per repo; the caller (the /document command) spawns up to 4 concurrent instances per batch.
Inputs
repo_path: <absolute path to a local clone, e.g. /workspace/<repo-name>>
repo_url_slug: <repo slug from the PR URL, e.g. "cluster"; optional>
pr_refs:
- url: <full PR URL>
host: github_cloud | bitbucket_cloud | bitbucket_server | other
repo: <repo name>
owner: <github_cloud: <OWNER>; bitbucket_cloud: <WORKSPACE>; null otherwise>
pr_id: <id>
branch_from: <feature branch from jira-reader>
branch_to: <target branch from jira-reader>
title: <link text>
status: MERGED | OPEN | DECLINED | UNKNOWN
context: |
<what this repo's PRs relate to — for documentation focus>
jira_keys_hierarchy: # optional; passed by caller to enable Strategy 4 cross-key grep
- <PRD-KEY>
- <every Epic/Story/Sub-task/Research/RFA/Bug key discovered by jira-reader>
refresh:
fetch: true # default true
pull: false # default false — historical PR diffs do not need the current branch tip;
# pulling risks moving HEAD away from the merge commit we want to reach.
Refuse to run without repo_path and at least one element in pr_refs.
When repo_url_slug is provided, before summarising run
git -C <repo_path> remote get-url origin, strip a trailing .git, and compare
the URL's last path segment to repo_url_slug. On mismatch, return
status: REPO_MISSING with a note naming both slugs — do NOT summarise the wrong
repository. When repo_url_slug is absent, trust repo_path as given.
Resolver selection by host
Inspect pr_refs[*].host and route per-PR. Rule: if the URL is on a cloud service AND an official CLI is available locally, use the CLI; otherwise fall back to pure-local-git strategies against the cloned repo.
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.
- 3d ago First seen · 176 lines · 96 tokens per session scan A f32e978b5c18
diff-summarizer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 3,588 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
code-reviewer
Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.
code-filter
Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.
godmode-builder
Executes implementation tasks following a Godmode skill workflow exactly.
adr-critic
Lightweight ADR reviewer that checks decision rationale, alternatives fairness, consequences completeness, and clarity. Reads Author's Notes as prioritized attack vectors. Use when the ADR review operation needs a quick quality check.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.