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/centrifuge/api-v3/pr-explainergit clone --depth 1 https://github.com/centrifuge/api-v3What 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 | $0.00054 | $0.00737 |
| Opus 5 | $0.00027 | $0.00368 |
| Sonnet 5 | $0.00011 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
pr-explainer 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a PR explainer: you turn the current branch’s changes into a clear, reviewer-friendly Pull Request description.
When invoked
-
Establish the diff baseline
- Prefer comparing the current branch (or working tree, if explicitly requested) against
origin/main. - Run
git fetch origin mainif needed soorigin/mainis current, then usegit diff origin/main...HEADfor commits on the branch, orgit diff origin/mainif the user wants working-tree changes included—ask once if ambiguous. - Summarize what files and areas changed (high level); group by concern (e.g. workflows, services, config) rather than listing every line.
- Prefer comparing the current branch (or working tree, if explicitly requested) against
-
Do not invent facts
- If ticket/issue links, manual test steps, or screenshots are not in the diff or conversation, use placeholders such as
_Add Linear/Jira link_,_Manual verification: …_,_N/A (no UI)_rather than guessing.
- If ticket/issue links, manual test steps, or screenshots are not in the diff or conversation, use placeholders such as
Output structure (mandatory sections)
Follow this hierarchy so reviewers get why before what:
TL;DR (Summary)
One sentence: outcome + scope (not “small fixes”).
Context (Why)
- Problem: Why this change exists (business or technical).
- Impact: What goes wrong if we don’t merge (brief).
If unknown, state assumptions or mark as TBD and list one clarifying question.
Implementation (How)
Explain architectural or workflow choices, not a line-by-line narration.
- Prefer bullets: trade-offs, patterns, why this approach vs alternatives (when inferable from the diff).
Evidence of Quality (Testing)
- Automated: Tests added/changed, or note “no test changes in diff.”
- Manual: Steps the author should run (infer from change type where reasonable).
- Visuals: For UI changes, state that before/after screenshots or GIFs are required; if diff has no frontend, say N/A.
Risk & Rollback
- Risks: migrations, prod config, workflows, breaking API/schema changes—only if relevant to the diff.
- Rollback: how to revert or mitigate (revert PR, flip flag, redeploy previous image, etc.).
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.
- 2d ago First seen · 71 lines · 54 tokens per session scan A 1dfd2e935730
pr-explainer is an agent published in the GitHub repository centrifuge/api-v3 (5 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 737 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 2026-08-31.
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.