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/read-codebase-context/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/read-codebase-context)<a href="https://agentmods.dev/skills/asta-nguyen/kamehadb/read-codebase-context"><img src="https://agentmods.dev/badge/skills/asta-nguyen/kamehadb/read-codebase-context/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/read-codebase-context"><img src="https://agentmods.dev/badge/skills/asta-nguyen/kamehadb/read-codebase-context.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 | $0.00046 | $0.01416 |
| Opus 5.5 | $0.00018 | $0.00566 |
| Sonnet 5.5 | $0.00009 | $0.00283 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
read-codebase-context 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read Codebase Context
Choose tools by purpose; current source and tests establish facts.
Refresh an impact map
When the active change's tasks.md (or a legacy plan) has an ## Impact map, first check that it has
Verified at: <full commit SHA>. Verify that commit exists and is an ancestor
of HEAD with git cat-file -e <sha>^{commit} and
git merge-base --is-ancestor <sha> HEAD. If the SHA is missing, unavailable,
or not an ancestor (for example, after a rebase), discard the map for
navigation and trace existing source below. When no commit existed at map
creation, re-trace existing source; if the planned source does not exist yet,
use the source-less map rule in step 5 instead of tracing a nonexistent flow.
For a valid SHA, run git status --short and
git diff --name-only <verified-sha> to find committed, staged, and unstaged
tracked changes since the map; add untracked paths from git status --short.
Re-trace changed and newly touched paths, then always run Confirm for every
entry-point and implementation symbol in the map across the current repository
using FFF multi-pattern grep or rg. Read current source for every file to
edit and every newly found caller. The map guides navigation, not evidence.
Trace and record the impact
- Check
docs/llm/AGENTS.mdanddocs/llm/INDEX.mdindependently. If both exist, read both and open the relevant linked page. If onlyINDEX.mdexists, read it, open a relevant linked page, and report the missingAGENTS.md. If onlyAGENTS.mdexists, read it, report the missing index and no verified wiki page coverage. If neither exists, report no verified wiki coverage and continue. If an existing index has no relevant linked page, report no verified coverage for this task and continue. - Search in this order: Locate → Expand → Confirm → Read. Each tool is optional; use the fallback when it is unavailable, fails, or returns irrelevant results. Do not retry a failed tool repeatedly.
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 · +3 lines a865f563f820
- 26d ago Changed · +2 lines b3bcf51af5da
- 1mo ago First seen · 99 lines · 46 tokens per session scan A 8221de8a15cc
read-codebase-context is a skill published in the GitHub repository asta-nguyen/kamehadb (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,416 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.
read-codebase-context compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| read-codebase-contextasta-nguyen/kamehadb | Skill | 14 | 10d ago | Apache-2.0 | A | 46 | 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 |