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 skills add GabsFranke/claude-code-github-agent --skill codebase-contextgit clone --depth 1 https://github.com/GabsFranke/claude-code-github-agentWrote 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/gabsfranke/claude-code-github-agent/codebase-context)<a href="https://agentmods.dev/skills/gabsfranke/claude-code-github-agent/codebase-context"><img src="https://agentmods.dev/badge/skills/gabsfranke/claude-code-github-agent/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/gabsfranke/claude-code-github-agent/codebase-context"><img src="https://agentmods.dev/badge/skills/gabsfranke/claude-code-github-agent/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 | $0.00156 | $0.01407 |
| Opus 5.5 | $0.00062 | $0.00563 |
| Sonnet 5.5 | $0.00031 | $0.00281 |
| Haiku 4.5 | $0.00016 | $0.00141 |
Grade A, and why
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 26d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Context Tools
You have CodeGraph MCP tools and built-in Claude Code tools for code exploration. Use them in order — start cheap, escalate only when needed.
Structural Map (always available)
When your session starts, you receive a repomap — a compact structural overview of the entire codebase injected into your system prompt. It shows ranked definitions (classes, functions, methods) with line numbers, like a table of contents:
shared/sdk_factory.py:
32│ class SDKOptionsBuilder
58│ function build_options
124│ method with_memory_mcp
services/sandbox_executor/sandbox_worker.py:
25│ function main
142│ function process_job
Generated via tree-sitter parsing and reference graph ranking, so the most important/referenced definitions appear first. Use it to:
- Quickly locate where things are defined before reading files
- Understand the overall shape of the codebase
- Know which files matter most for a given task
The repomap is personalized toward files relevant to your task (e.g., changed files in a PR review).
CodeGraph MCP Tools (needs codegraph init -i)
These 10+ tools use the code graph (call edges, import edges, inheritance) via the CodeGraph MCP server. They run as a separate stdio MCP server (codegraph serve --mcp) and query a local SQLite database. If CodeGraph is not installed, these tools are simply unavailable — no errors, just no graph intelligence.
codegraph_search
Find symbols by name across the codebase. Returns kind, location, and signature.
codegraph_context
Primary discovery tool. One call returns entry points, related symbols, and code snippets. Use this first for "how does X work?" questions.
codegraph_context(task="how does the queue handle retries")
codegraph_trace
Trace the call path between two symbols ("how does X reach Y"). Each hop includes the source body inline. Follows dynamic-dispatch hops that grep can't.
codegraph_trace(from="process_job", to="execute_sdk_loop")
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.
- 26d ago Changed · -104 lines · +11 tokens per session ada324a17470
- 1mo ago First seen · 227 lines · 145 tokens per session scan A c95773ec0fa7
codebase-context is a skill published in the GitHub repository GabsFranke/claude-code-github-agent (5 stars, last pushed 26d ago), licensed MIT. It adds 156 tokens to every session and 1,407 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…