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 turbyho/fw-context-mcp --skill fw-reviewgit clone --depth 1 https://github.com/turbyho/fw-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/turbyho/fw-context-mcp/fw-review)<a href="https://agentmods.dev/skills/turbyho/fw-context-mcp/fw-review"><img src="https://agentmods.dev/badge/skills/turbyho/fw-context-mcp/fw-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/turbyho/fw-context-mcp/fw-review"><img src="https://agentmods.dev/badge/skills/turbyho/fw-context-mcp/fw-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 | $0.00000 | $0.03973 |
| Opus 5.5 | $0.00000 | $0.01589 |
| Sonnet 5.5 | $0.00000 | $0.00795 |
| Haiku 4.5 | $0.00000 | $0.00397 |
Grade A, and why
fw-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 17d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
- Review of diffs, commits, or specific changed files in embedded C/C++ projects
- Bugs, behavioral regressions, runtime risks, concurrency, memory, and platform rule violations
- Changes outside firmware code (docs, CI, scripts, plans) — skip fw-context, review manually
CRITICAL — MANDATORY
For C/C++ source code, use ONLY fw-context tools for reading, searching, and browsing files.
MUST NOT use any other tool to read or search C/C++ source. fw-context provides
ifdef-filtered code — only what actually compiles for the build of the query.
Other tools show unprocessed preprocessor noise including dead #ifdef branches.
MUST NOT skip Phase 0. Every review MUST begin by creating and writing out the plan.
Core principle — verify in full project context
Every code change MUST be verified recursively against the entire project, not just the local diff fragment. A change that looks correct in isolation can be wrong in the broader context. For every changed symbol (function, type, macro):
- Callers — who calls this? Were they all updated? Use
find_callersthenfind_all_callers_recursivefor the full call tree. - Callees — what does this call? Is the new behavior still compatible with downstream
dependencies? Use
get_symbol_contextorfind_callees_recursive. - Users — who reads/writes this type or variable? Use
find_references. - Duplicates — does a similar implementation exist elsewhere? Use
search_bodiesand scan ALL results. - Removals — is the removed symbol truly gone from every file? Use
search_contentto confirm zero results project-wide. - Dead code — did the removal leave orphaned functions? Use
find_dead_code.
The diff shows SCOPE. fw-context verifies CORRECTNESS. Never conclude a review from the diff alone.
Read every page
A tool that gives a long list pages it. The answer holds a page notice with total,
offset, shown and more (a dict answer holds it under the key page).
- When
moreis true, call again withoffset=<offset + shown>. Thehintgives that call.read_filepages lines: call again with thestart_linethat itshintnames. - Do NOT conclude "that is all of them" from one page. Read
total.
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.
- 17d ago Changed · +23 lines a900358f5ab4
- 1mo ago Changed · +2 lines 727296c66ead
- 2mo ago Changed 3b42f4398a1c
- 2mo ago First seen · 231 lines · 0 tokens per session scan A c9f742b54798
fw-review is a skill published in the GitHub repository turbyho/fw-context-mcp (10 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,973 tokens. 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.
fw-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fw-reviewturbyho/fw-context-mcp | Skill | 10 | 18d ago | MIT | A | 0 | Claude Code, Codex |
| connector-sdk-submitfivetran/connector_sdk_tools | Skill | 89 | yesterday | MIT | A | 45 | Claude Code |
| esp32-arch-reviewagodianel/esp32-claude-workbench | Skill | 82 | 4d ago | MIT | A | 124 | Claude Code, Codex |
| kicad-pcb-reviewoaslananka/kicad-mcp-pro | Skill | 182 | yesterday | MIT | A | 31 | Claude Code |
| kicad-pcb-reviewoaslananka/kicad-mcp-pro | Skill | 182 | yesterday | MIT | A | 19 | Claude Code |
| vllm-rocm-pr-reviewshen-shanshan/vllm-dev-skills | Skill | 31 | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |
| rtl-reviewvibeic/vibe-ic | Skill | 32 | today | Apache-2.0 | A | 63 | Claude Code |