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 sjarmak/coding-agent-workflows --skill code-graphgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/sjarmak/coding-agent-workflows/code-graph)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/code-graph"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/code-graph/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/sjarmak/coding-agent-workflows/code-graph"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/code-graph.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 | $0.00032 | $0.00513 |
| Opus 5.5 | $0.00013 | $0.00205 |
| Sonnet 5.5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
code-graph 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 16d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code graph navigation
Use for investigations that span files, call chains, or change impact. Read-only by default. Prefer the repository's code-search specialist for substantial investigations; pass the absolute repository path, revision, question, and acceptance criteria. Simple symbol lookups can stay local.
Choose the graph by capability
- Codegraph: source navigation, callers, callees, and impact. Discover the actual exposed tools; prefer
codegraph_explorewith an explicitprojectPath. Ask a focused question or name symbols. Older per-operation MCP names are not guaranteed. - codebase-memory: arbitrary graph queries, cross-service edges, schema exploration, degree analysis, ADR or trace integration. Use the
codebase-memoryskill only if the needed capability is exposed. - Graphify: persistent relationships across code, documents, papers, and other media. Use
graphifyfor those questions whengraphify-out/exists. - No index or unavailable tool: use
rg, file listings, and targeted source reads. Do not initialize an index just to answer a question.
Evidence contract
- Establish repository and revision. Respect pending-sync, disabled auto-sync, omitted source, and changed-on-disk warnings.
- Use returned source as already read. Read disk only to fill a specific gap or resolve stale source. Edges can remain stale even when returned source is current.
- Distinguish structural edges, inferred relationships, and runtime traces. Same-name symbols do not establish dispatch; missing edges do not prove dead code.
- Follow the relevant caller and downstream paths, including error and lifecycle paths. Stop when evidence answers the question, not when every neighbor has been expanded.
- Return source-cited findings, affected contracts, recommended change locations, and coverage limits. Do not repeat a graph query with a full-tree search unless the graph left a specific gap.
CLI and setup
For a CLI-only environment inspect codegraph --help and codegraph status --help before choosing installed-version options. Setup is separate from navigation. codegraph install --print-config codex previews configuration; install, init, index, and sync can change configuration or state. Configure the chosen project and runtime only when setup is requested. Never copy another workstation's credentials or blanket permission list.
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.
- 16d ago First seen · 28 lines · 32 tokens per session scan A 57bdffb6dbb1
code-graph is a skill published in the GitHub repository sjarmak/coding-agent-workflows (6 stars, last pushed 17d ago), licensed MIT. It adds 32 tokens to every session and 513 once invoked, about $0.0001 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 2026-10-02.
Other skills, from other repositories
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
ego-lite-simplify
Find and implement evidence-backed simplifications in the ego-lite repository. Use when reviewing the codebase for dead code, duplicated state or APIs, speculative abstractions, unnecessary compatibility layers, hand-written infrastructure, excessive tests or documentation, or when the user asks to reduce code size or…
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".