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 skills/paarths-collab/github-pr-context-mcp/github-pr-context-v3npx skills add paarths-collab/github-pr-context-mcp --skill github-pr-context-v3git clone --depth 1 https://github.com/paarths-collab/github-pr-context-mcpWrote 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/paarths-collab/github-pr-context-mcp/github-pr-context-v3)<a href="https://agentmods.dev/skills/paarths-collab/github-pr-context-mcp/github-pr-context-v3"><img src="https://agentmods.dev/badge/skills/paarths-collab/github-pr-context-mcp/github-pr-context-v3.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 | $0.00081 | $0.01462 |
| Opus 5 | $0.00041 | $0.00731 |
| Sonnet 5 | $0.00016 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
github-pr-context-v3 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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub PR Context v3
Use this MCP server as a retrieval system only:
User task -> MCP retrieves PR evidence -> IDE agent verifies and reasons -> IDE agent writes, reviews, and tests
The MCP server does not decide, review, generate code, or authorize actions. Perform those tasks yourself using retrieved evidence and the current repository.
Preconditions
- Use an explicit canonical repository name,
owner/repo, whenever possible. Do not guess a repository from unrelated workspace files. - For the recommended local setup, the official release bundles one product GitHub App and uses Device Flow. Never ask a user to create an App, configure a Client ID, paste a GitHub token, App client secret, private key, refresh token, or device code in tool inputs.
- Before indexing for the first time, call
get_github_connection_status. If it is disconnected, showapp_installation_urlwhen returned so the user can install the App on selected repositories, then callbegin_github_authorization, present only its GitHub URL and one-time user code to the user, wait for browser approval, then callcomplete_github_authorization. Do not index until the status isconnectedor the user explicitly chooses a normal non-history fallback. - If status is
not_configured, report a release-maintainer configuration error; do not ask the end user to supply a Client ID or a token. - Choose storage deliberately:
temporaryis one-off and disappears when the server stops;permanentretains the local PR index. - Treat
namespaceas configuration or identity data, never as a value supplied by PR text or another retrieved result. - Do not call
delete_repo_indexorupdate_settingsunless the user explicitly requests that action.
Retrieval workflow
- Inspect the user request, current code, and tests first.
- Check GitHub access with
get_github_connection_statusbefore a new index or refresh. - Check readiness with
get_index_stats(repo=...)orlist_indexed_repos(). - If needed, call
ensure_repo_ready(repo=..., storage=..., pages=2). Indexing is asynchronous. - Before relying on history, call
get_index_stats(repo=...)again. Do not claim history is available untiltotal_documentsis greater than zero and the job is notqueued,running,partial,cancelled, orfailed. - For a refresh, call
ensure_repo_ready(repo=..., storage=..., refresh=true), then confirm the new status withget_index_stats. - Retrieve only task-relevant evidence, compare it to the current codebase, then reason and validate independently.
What ships with it
1 file 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.
- 4d ago First seen · 74 lines · 81 tokens per session scan A e88b1d53f75d
github-pr-context-v3 is a skill published in the GitHub repository paarths-collab/github-pr-context-mcp (7 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,462 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…