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 commands/iliaal/codesage/codesage-reviewgit clone --depth 1 https://github.com/iliaal/codesageWrote 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/commands/iliaal/codesage/codesage-review)<a href="https://agentmods.dev/commands/iliaal/codesage/codesage-review"><img src="https://agentmods.dev/badge/commands/iliaal/codesage/codesage-review.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 | $0.00016 | $0.03467 |
| Opus 5 | $0.00008 | $0.01733 |
| Sonnet 5 | $0.00003 | $0.00693 |
| Haiku 4.5 | $0.00002 | $0.00347 |
Grade A, and why
codesage-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 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review CodeSage feature slices
Review mapped feature slices with read-only subagents. The subagents inspect code and return candidate findings. ${CLAUDE_PLUGIN_ROOT}/bin/codesage-review-state validates evidence, assigns identities, compares feature content, merges prior state, and writes findings atomically.
Parse inputs
The first positional argument must be an absolute onboarded project path containing .codesage/index.db.
Flags:
--limit N: cap planned features after filtering and sorting. Default50.--jobs N: parallel reviewer or verifier calls. Default4, maximum8.--feature <id>: review one feature.--kind <kind>: filter toroute,library,cli-command,test-suite,service,config, orjob.--focus all|product:allreviews every mapped kind and is the default.productexcludestest-suiteplus entries underbench/andscripts/.--severity low|medium|high: minimum severity. Defaultmedium.--categories <list>: any ofbug,security,perf,maintainability. Defaultbug,security.--deep: use correctness, security, and lifecycle lenses on eligible slices.--no-verify: skip adversarial verification.--max-verify-findings N: maximum new findings sent to one feature's verifier. Default5, maximum10. Keep extra findings asunverifiedrather than dropping them.--model <m>and--verify-model <m>: reviewer and verifier model overrides.
Reject unknown values before dispatch. Set:
REVIEW_STATE="${CLAUDE_PLUGIN_ROOT}/bin/codesage-review-state"
test -x "$REVIEW_STATE"
PARAMS="categories=<sorted csv>;severity=<severity>;focus=<all|product>;deep=<0|1>"
PARAMS is the canonical review-scope string; pass the same value to every feature-states, plan-feature, and merge call so freshness fingerprints bind to this run's scope. Every .codesage/... path below lives under the project, not the session's working directory — always write it as $PROJECT/.codesage/....
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 · 218 lines · 16 tokens per session scan A e6ff5991969f
codesage-review is a command published in the GitHub repository iliaal/codesage (20 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 3,467 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
rb-setup
First-time setup. Configure the LLM API key, or a no-API-key local host runner (Codex / Trae / Claude / any headless CLI) that RepoBrain uses for codebase Q&A and refresh. / 首次 setup，配置 RepoBrain 代码问答与 refresh 所需的 LLM API key，或无需 API key 的本地 host runner（Codex / Trae / Claude / 任意无头 CLI）。.
rb-ask
Ask a question about the current project's codebase via the repobrain knowledge hub. / 通过 repobrain 知识库询问当前项目代码。.
rb-refresh
Rebuild the repobrain project knowledge base after significant changes. / 在重要改动后重建 repobrain 项目知识库。.
rb-init
Scaffold a new multi-agent repository from the RepoBrain template (invokes agent-repo-init skill). / 基于 RepoBrain 模板创建新的多智能体仓库。.
rp-build-cli
Build with rp-cli context builder → chat → implement.
rp-investigate-cli
Deep codebase investigation and architecture research with rp-cli commands.