Borrowing it
Nothing to install: this file belongs to asta-nguyen/kamehadb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/asta-nguyen/kamehadb/main/.agents/skills/setup-codebase/SKILL.mdgit clone --depth 1 https://github.com/asta-nguyen/kamehadbWrote 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/asta-nguyen/kamehadb/setup-codebase)<a href="https://agentmods.dev/skills/asta-nguyen/kamehadb/setup-codebase"><img src="https://agentmods.dev/badge/skills/asta-nguyen/kamehadb/setup-codebase/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/asta-nguyen/kamehadb/setup-codebase"><img src="https://agentmods.dev/badge/skills/asta-nguyen/kamehadb/setup-codebase.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 | $0.00050 | $0.02046 |
| Opus 5.5 | $0.00020 | $0.00818 |
| Sonnet 5.5 | $0.00010 | $0.00409 |
| Haiku 4.5 | $0.00005 | $0.00205 |
Grade A, and why
setup-codebase 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 19d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Codebase
Create context with repository-reading, not a static file template. Existing context belongs to the project: never overwrite or shorten it.
Pick the mode before step 1; this guard runs before any write.
| Mode | Caller | What to run |
|---|---|---|
| Inline wiki | document-wiki |
Only the docs/llm/ skeleton part of step 3; read back the created wiki files and return. Do not create or update AGENTS.md, CLAUDE.md, or CONVENTIONS.md, capture conventions, query OpenEZ, change .gitignore, or run other steps. |
| Code task | using-devkit, brainstorm-feature, or plan-feature |
Create only necessary missing repository context; skip the wiki skeleton unless wiki setup was requested. An existing wiki stays available for document-wiki's ## Task updates. |
| Direct | The user asks for setup | The full procedure; run step 4's preflight before step 3 writes anything. |
- Check the exact status of
AGENTS.md,CLAUDE.md,CONVENTIONS.md,docs/llm/, and.gitignore. Read every existing context or conventions file before writing anything. If the repository has no application source and an approved design exists asdesign.mdin adocs/agent-devkit/changes/folder (or a legacy spec underdocs/agent-devkit/specs/), read it before writing context. - If context is missing, inspect only enough evidence to ground it:
README*, root/workspace manifests, task scripts, environment examples, CI/config, top-level source layout, and any approved design from the previous step. Do not install dependencies, start services, or infer facts from filenames alone. - Write only missing files from that evidence:
-
AGENTS.md: concise purpose, relevant layout, verified commands, explicit conventions/gotchas, and verification. Omit unknown sections. For a source-less new project, the approved design establishes intended purpose and planned layout only; do not claim unimplemented behavior or commands as verified. If askills/or.agents/skillsfolder exists in the repository, add a## Skillssection listing each skill by name with itsSKILL.mdpath so every agent platform can discover them. Ifdocs/llm/exists or is created, add a## Documentationsection:## Documentation The verified codebase wiki is at `docs/llm/INDEX.md`. For behavior, workflow, or domain questions: 1. Read `docs/llm/INDEX.md`. 2. Open the relevant wiki page. 3. Verify important claims against current source and tests. The wiki describes verified behavior only; source and tests remain authoritative. -
CLAUDE.md: a short repository-specific pointer toAGENTS.md; include extra instructions only when local evidence establishes them. -
docs/llm/: for direct setup or wiki-only inline calls, create the wiki skeleton withAGENTS.mdandINDEX.md; skip for a code-task call without an explicit wiki-setup request. The generatedAGENTS.mdmust matchdocument-wiki's current-source verification rules, distinguish verification limits from confirmed content gaps, and state that any existing log is legacy, not read or written and not used for freshness. It must also state that feature pages usedocument-wiki's requirement format and the## Requirement prefixesregistry inINDEX.md, without restating the format. Do not createLOG.md. If a legacyLOG.mdalready exists, preserve it byte-for-byte without reading or updating it. Create wiki category folders (architecture/,domains/,workflows/,integrations/,operations/, ordecisions/) only whendocument-wikihas a real page to place there; do not add placeholder pages just to preserve empty directories.
-
What ships with it
1 file 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.
- 19d ago Changed · -19 lines f9fc559e4ede
- 26d ago Changed · +12 lines 1ab4b4e8f927
- 1mo ago First seen · 157 lines · 50 tokens per session scan A 123a2424326e
setup-codebase is a skill published in the GitHub repository asta-nguyen/kamehadb (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,046 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-05.
setup-codebase compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setup-codebaseasta-nguyen/kamehadb | Skill | 14 | 10d ago | Apache-2.0 | A | 50 | Claude Code, Codex |
| chromaNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 12 | Claude Code, Codex |
| backend-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 51 | Claude Code, Codex |
| database-migrationsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 61 | Claude Code, Kiro |
| postgres-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 45 | Claude Code, Kiro |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 12k | yesterday | CC0-1.0 | A | 116 | Claude Code, Codex |
| review-prsgoogleapis/mcp-toolbox | Skill | 17k | yesterday | Apache-2.0 | A | 162 | Claude Code, Codex |