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 MarcinHamiga/code-indexing-mcp --skill indexed-reviewgit clone --depth 1 https://github.com/MarcinHamiga/code-indexing-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/marcinhamiga/code-indexing-mcp/indexed-review)<a href="https://agentmods.dev/skills/marcinhamiga/code-indexing-mcp/indexed-review"><img src="https://agentmods.dev/badge/skills/marcinhamiga/code-indexing-mcp/indexed-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/marcinhamiga/code-indexing-mcp/indexed-review"><img src="https://agentmods.dev/badge/skills/marcinhamiga/code-indexing-mcp/indexed-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 | $0.00042 | $0.01171 |
| Opus 5 | $0.00021 | $0.00585 |
| Sonnet 5 | $0.00008 | $0.00234 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
indexed-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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running a structured, angle-focused code review. Follow this workflow exactly.
1. Require a review angle
The review angle is $angle (valid examples: security, logic, UI, UX, performance, architecture, API design, error handling, testing).
If no angle was provided (or it is ambiguous), you MUST stop and ask the user with the AskUserQuestion tool before doing any analysis. Offer these options:
- security — vulnerabilities, injection, secrets, authn/authz, unsafe input handling
- logic — correctness, edge cases, error handling, race conditions, off-by-one
- UI / UX — interface structure, consistency, accessibility, user-facing flows
- performance — hot paths, allocations, I/O patterns, caching, complexity
Do not guess the angle. A review without a stated angle is not started.
Scope is $scope (a directory, module, feature, or symbol set). If scope is empty, ask the user or infer it from their request (e.g. recent changes); state the scope you settled on before reviewing.
2. Prepare the index
- Call
mcp__code-indexing-mcp__project_statusfor the target project. If the project is unknown, callmcp__code-indexing-mcp__list_projectsand, if needed,mcp__code-indexing-mcp__init_project. - If the index is missing or stale relative to the files under review, call
mcp__code-indexing-mcp__index_projectfirst. Tell the user if indexing will take a moment.
3. Analyze with the index, not grep
This is the core rule of this skill: use the code-indexing-mcp tools as the primary navigation and analysis mechanism. Do not fall back to Grep/Glob for code exploration.
mcp__code-indexing-mcp__search_code— semantic natural-language queries to find relevant code for the angle (see playbooks below). Issue several targeted queries, not one broad one.mcp__code-indexing-mcp__file_outline— get a file's structure before reading it; decide which parts matter instead of dumping whole files.mcp__code-indexing-mcp__find_symbol— resolve a function/class name to its definitions when evaluating impact or correctness. It matches declaration names only; usemcp__code-indexing-mcp__find_referencesfor call sites.mcp__code-indexing-mcp__get_chunk— pull the full body of a chunk returned by search when you need exact code.
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.
- 8d ago First seen · 67 lines · 42 tokens per session scan A cc1994bc2c72
indexed-review is a skill published in the GitHub repository MarcinHamiga/code-indexing-mcp (0 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,171 once invoked, about $0.0002 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…