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 saski/arnesto --skill codegraphgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/codegraph)<a href="https://agentmods.dev/skills/saski/arnesto/codegraph"><img src="https://agentmods.dev/badge/skills/saski/arnesto/codegraph/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/saski/arnesto/codegraph"><img src="https://agentmods.dev/badge/skills/saski/arnesto/codegraph.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 | $0.00067 | $0.00807 |
| Opus 5.5 | $0.00027 | $0.00323 |
| Sonnet 5.5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
codegraph 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 9d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeGraph
Use a local structural index to locate relevant code, then read the actual source and tests before drawing conclusions or editing. The index is evidence for navigation, not proof that every dynamic reference has been found.
Choose the scope
- Identify the exact repository and the question to answer. Prefer
rgfor a simple literal lookup; do not create an index merely because the tool exists. - Inspect an existing
.codegraph/and its configuration before changing it. Never index a home directory, filesystem root, or unrelated repositories. - Indexing creates local SQLite state and an internal
.codegraph/.gitignore. Review exclusions first, especially secrets, generated files, and vendor code. Keep the index out of Git; do not loosen exclusions to increase counts.
Use the CLI
The reviewed package is @colbymchenry/[email protected] (MIT). The npm
distribution includes a platform runtime; npm still needs Node to launch the
shim. See usage and sources for setup and test evidence.
Set these for every invocation, including through a client MCP environment:
export DO_NOT_TRACK=1
export CODEGRAPH_TELEMETRY=0
export CODEGRAPH_NO_UPDATE_CHECK=1
From the selected repository, after checking the initialization side effects:
npx --yes @colbymchenry/[email protected] init .
npx --yes @colbymchenry/[email protected] status .
npx --yes @colbymchenry/[email protected] query 'symbol_name' --path . --json
npx --yes @colbymchenry/[email protected] callers 'symbol_name' --path . --json
Run initialization interactively. Choose manual synchronization if it offers
Git hooks. Do not pass init --yes in a Git repository: that flag can install
hooks when the native watcher is unavailable. The npx --yes above only accepts
the package download; it is a different flag.
For an existing index after edits, run sync . with the same version and
environment. Use --help for explore, node, callees, or impact before
constructing a more specific query. Do not treat an empty or stale index as
evidence of no callers. Fall back to source search if indexing fails or the
language is unsupported.
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.
- 9d ago First seen · 78 lines · 67 tokens per session scan A cf20f45f3a69
codegraph is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed yesterday), licensed Unlicense. It adds 67 tokens to every session and 807 once invoked, about $0.0003 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 2026-10-08.
Other skills, from other repositories
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
address-pr-comments
Work through the review comments on a pull request: check each point against the code, make the changes that are right, answer the ones that are not, and hold every reply for approval before it is posted.
code-refiner
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting".
package-optimizer
Evaluate one existing package or bounded package family from recorded evaluator evidence and a capability profile, then propose retain, simplify, strengthen, retire, or inconclusive without editing. Use when optimizing a skill, agent, hook, rule, command, utility, or preset; evaluating whether package detail is…