Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sd0xdev/sd0x-harnessnpx agentmods add skills/sd0xdev/sd0x-harness/repo-intakeWrote 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/sd0xdev/sd0x-harness/repo-intake)<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/repo-intake"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/repo-intake/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/sd0xdev/sd0x-harness/repo-intake"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/repo-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.01120 |
| Opus 5 | $0.00030 | $0.00560 |
| Sonnet 5 | $0.00012 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
repo-intake 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 6d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Intake
When to Use
- First time onboarding a project
- Rebuilding cache after major project structural changes
- Cache expired, needs updating
When NOT to Use
- Already familiar with project structure (read cache directly)
- Only need to find specific files (use Glob/Grep)
- Day-to-day development (cache already exists)
Workflow
Docs -> Entrypoints -> Tests Map -> Next Steps
Usage
bash scripts/run-skill.sh repo-intake intake_cached.js --mode auto --top 10
Manifest Map（宣告依賴地圖）
Monorepo / multi-package repo 的 workspace 拓撲與宣告依賴圖。邊語義是
declares_dependency——manifest 裡寫了什麼，不證明 import、呼叫或 runtime 影響。
一律 fail-closed：整份檔案無法讀取／UTF-8 解碼、或 JSON document 無法解析則記
coverage skipped；已進入 Go/TOML recognizer 的相關不支援 construct 則記
partial。絕不產生猜測邊。
bash scripts/run-skill.sh repo-intake manifest_map.js # overview (md)
bash scripts/run-skill.sh repo-intake manifest_map.js --format json # 完整 envelope
bash scripts/run-skill.sh repo-intake manifest_map.js --reverse <selector> # 誰宣告依賴它
bash scripts/run-skill.sh repo-intake manifest_map.js --cycles # 宣告環偵測
| Flag | 說明 |
|---|---|
--format md|json |
預設 md；json 為完整 artifact，不受 --top 截斷 |
--top N |
md 清單截斷（預設 12） |
--reverse <sel> |
selector：節點 ID（ws:node:packages/a）或名稱（node:lodash / lodash）；多重匹配 exit 2 並列出候選 |
--cycles |
與 --reverse 互斥 |
--include-candidates |
把未經 controller 確認的 candidate workspace 納入架構節點集（預設排除） |
生態系：node / php / go / rust / python（辨識 manifest 見
scripts/config/repo-intake.json 的 manifest_map 段）。無效參數 exit 2。
資料模型、解析矩陣與凍結語法契約：references/manifest-map.md；完整規格：
docs/features/repo-intake-manifest-map/2-tech-spec.md。
Cache Location
Cache stored at: ~/.claude/cache/repo-intake/<repoKey>/
| File | Description |
|---|---|
latest.md |
Latest scan results |
latest.json |
Latest scan results (JSON) |
LATEST.json |
Cache metadata |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 130 lines · 60 tokens per session scan A d8467dd277d5
repo-intake is a skill published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 1,120 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
comet-classic
A Chinese-language workflow guide for starting or resuming a structured software change using OpenSpec and Superpowers.
comet-native
A workflow for managing Native changes in Comet, where requirements, progress, and acceptance results are saved in project files. It uses the Comet command-line runtime to move through defined work stages.
comet-build
A Comet workflow step for turning an approved design into an implementation plan and completed code changes. Comet is the project workflow system described by the add-on.
comet-github-idea-to-issue
A workflow for turning a local idea, bug observation, or improvement proposal into a focused GitHub Issue draft. GitHub Issues are shared records for bugs, features, questions, and maintenance work.
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.