ContextForge is an open-source gateway and registry that brings MCP, A2A, REST, and gRPC tools, agents, and APIs together behind one endpoint. It helps teams discover, govern, observe, authenticate, and route calls across AI infrastructure. The catalogue add-ons support operating and extending this gateway.
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 skills add IBM/mcp-context-forge --skill pr-reviewgit clone --depth 1 https://github.com/IBM/mcp-context-forgeWrote 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/ibm/mcp-context-forge/pr-review)<a href="https://agentmods.dev/skills/ibm/mcp-context-forge/pr-review"><img src="https://agentmods.dev/badge/skills/ibm/mcp-context-forge/pr-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ibm/mcp-context-forge/pr-review"><img src="https://agentmods.dev/badge/skills/ibm/mcp-context-forge/pr-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00057 | $0.01821 |
| Opus 5.5 | $0.00023 | $0.00728 |
| Sonnet 5.5 | $0.00011 | $0.00364 |
| Haiku 4.5 | $0.00006 | $0.00182 |
Grade A, and why
pr-review 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 today.
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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review
A review reports every issue as a finding the author can act on. A review changes no files.
Rebase on origin/main
- Run
git fetch origin. - Run
git rebase origin/main.
If the rebase hits conflicts, resolve them. When both sides changed the same logic substantively, ask the user which side wins. Resolve .secrets.baseline conflicts with the secret-detection skill.
Gather Context
- Diff: Collect all changes between
origin/mainand HEAD, plus staged and unstaged working-tree changes. Treat them as one unit. Staging status is never a finding. - PR metadata: When a PR exists, read the description, review comments, and linked issues (
gh pr view,gh pr view --comments,gh issue view N). - Scope: Compare the PR description against the linked issues. Partial coverage of an issue is acceptable when the PR says so. Unstated gaps and scope drift are findings.
- Conventions: Read
AGENTS.mdandCONTRIBUTING.md. Use their linter and test commands exactly.
Review Order
Review the diff in this order. Severity comes from Blocking Criteria below, not from the category.
- Security: injection, leaked secrets, auth gaps, OWASP top 10, Layer 1 / Layer 2 violations.
- Correctness: logic errors, edge cases, mismatch with linked issues.
- Test coverage: changed code has tests, including deny-path tests for security changes.
- Linter compliance: run project linters on touched files and report violations. Do not fix them (see Optional Lint Auto-Fix).
- Performance: N+1 queries, unnecessary allocations, bottlenecks.
- Redundancy: duplicated logic, copy-paste patterns, shared-utility opportunities.
- Design: structural quality (see Design Guidance).
- Consistency: adherence to documented conventions.
- Alembic migrations (conditional): idempotence, reversibility, cross-database compatibility,
batch_alter_tablefor SQLite. Apply thealembic-migrationsskill.
Optional Lint Auto-Fix
Never auto-fix formatting during a review. A reviewer who edits the reviewed code changes the PR under review. Report black, isort, autoflake, pylint, bandit, and mypy findings for the author to address. Include the exact command and output.
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.
- today First seen · 148 lines · 57 tokens per session scan A 1c1b0bce434a
pr-review is a skill published in the GitHub repository IBM/mcp-context-forge (4,832 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 1,821 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-17.
pr-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pr-reviewIBM/mcp-context-forge | Skill | 4.8k | today | Apache-2.0 | A | 57 | Claude Code, Codex |
| migration-reviewrohitg00/ai-engineering-from-scratch | Skill | 79k | yesterday | MIT | A | 35 | Claude Code |
| otto-pr-review-loopomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 17 | Claude Code, Codex |
| adk-go-self-reviewgoogle/adk-go | Skill | 9.0k | today | Apache-2.0 | A | 87 | Claude Code, Codex |
| learn-from-sagekirodotdev/KiroCrew | Skill | 5.0k | today | Apache-2.0 | A | 56 | Claude Code, Codex |
| factory-gitlab-rereviewmastra-ai/mastra | Skill | 30k | today | none | A | 23 | Claude Code, Codex |
| code-standardsmastra-ai/mastra | Skill | 30k | today | none | A | 15 | Claude Code, Codex |