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-reportgit clone --depth 1 https://github.com/iliaal/codesageWhat 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 | $0.00024 | $0.01451 |
| Opus 5 | $0.00012 | $0.00726 |
| Sonnet 5 | $0.00005 | $0.00290 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade A, and why
codesage-report 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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Render codesage findings as Markdown
Format the project's findings into a Markdown report suitable for pasting into a PR description, a ticket, or a stakeholder email. No LLM call — this is a pure file walk + format.
Before touching any
.codesage/path:.codesage/is repository content, so a cloned repo can ship it — or any directory under it — as a symlink. Refuse to read, write, create, or delete through one. Check withtest -L <path>(nottest -e, which follows links) on.codesageitself and on each subdirectory you are about to use, and stop with an error if any is a symlink. Apply the same check to every leaf you touch: a*.jsonfindings file, or any temporary file you create beside it, may itself be a planted symlink or a directory. Read or write a leaf only if it is a regular file (or absent, when creating), and give temporary files a freshly generated unique name rather than a predictable one.
Parse arguments
First positional: absolute project path (required).
Filters (intersected — multiple filters AND together):
--status <s,s>— comma-separated, defaultopen,wont-fix. Triaged-out states (false-positive,fixed) excluded unless explicitly named.--severity <s,s>— defaulthigh,medium,low(all).--category <c,c>— default all.--feature <id>— restrict to one feature's findings.
Output:
--output <path>/-o <path>— write Markdown to this path. Without it, print to stdout.
Walk the findings
Read every .codesage/findings/<feature_id>.json in the project. For each finding, apply filters. Drop anything that doesn't match.
If the resulting set is empty after filtering, write:
No findings match the requested filters.
Project: <path>
Filters: status=<>, severity=<>, category=<>
Then list the unfiltered totals so the user can adjust:
Total findings in project: 47
By status: open: 23, fixed: 12, false-positive: 8, wont-fix: 4
By severity: high: 5, medium: 28, low: 14
By category: bug: 19, security: 11, perf: 9, maintainability: 8
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.
- 2d ago First seen · 136 lines · 24 tokens per session scan A 2acc437bf85b
codesage-report is a command published in the GitHub repository iliaal/codesage (20 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,451 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.