codegraph

A code-tracing skill that uses a stored graph of code relationships to follow execution paths that ordinary file searches may miss. It focuses on Python routing, events, callbacks, and other indirect connections.

In plain words
What is it for?
It is for tracing FastAPI or Django routes, event emitter loops, callback handlers, and abstract dispatch paths.
Why use it?
It helps reveal how code runs when functions are connected through decorators, event names, or other runtime configuration.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sponge-b0b/polaris/codegraph
Any agent
npx skills add sponge-b0b/Polaris --skill codegraph
Clone the repo
git clone --depth 1 https://github.com/sponge-b0b/Polaris

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.00698
Opus 5 $0.00030 $0.00349
Sonnet 5 $0.00012 $0.00140
Haiku 4.5 $0.00006 $0.00070

Measured 2d ago against content hash cbca3b84af68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.agents/skills/codegraph/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeGraph Analysis Skill

Objective

Expose the dynamic edge-synthesizer engine to trace implicit Python execution flows, runtime framework routing configurations, asynchronous event loops, and string-keyed callbacks that static AST tools or raw grep queries miss.

Context Inputs

  • Authoritative Edge Registry: .codegraph/ (Driven by a native, always-on SQLite backend).
  • Live File Watcher: The underlying MCP background daemon runs an active background filesystem watcher. It automatically captures file saves and incrementally syncs the graph under a second—manual index rebuilds are completely unnecessary.

Guardrail Constraints

  • Edge Resolution Invariant: Only trust edges that resolve completely from end to end.
  • Blind-Spot Rule: If a trace yields a partial or broken path matching an interface boundary, log it explicitly as a "CodeGraph blind spot." Stop digging through files along that specific trajectory to avoid generating unnecessary file-read overhead.
  • Staleness Detection (Debounce Window): If you make a rapid succession of edits, CodeGraph might display a minor staleness banner (⚠️) for a few milliseconds while the quiet window processes. If you see this banner, read the modified target file directly instead of over-relying on the graph query.

Execution Steps

When investigating runtime call paths, decoupled handlers, or asynchronous routing flows, run the CodeGraph tools based on your investigative intent:

1. Verification of System Pathing & Readiness

Before initializing dynamic code exploration, verify that the local repository background daemon is healthy and connected:

  • Run: codegraph status to validate the state of the active tracking databases.

2. High-Efficiency Single-Pass Single Symbol Exploration

Gather callers, callees, structural dependencies, and impact radii for a specific function name, class, or decorator target in one command without manual sweeps:

  • Run: codegraph_explore(query="<symbol_name>") via the native MCP tool connector.

Read the full file on GitHub · 54 lines

Changes

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.

  1. 2d ago First seen · 54 lines · 59 tokens per session scan A cbca3b84af68

Subscribe to this mod's changes

codegraph is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 698 once invoked, about $0.0003 per session on Opus 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.

Related

Other skills, from other repositories

release

Cut a versioned release of the DOS kernel — bump the version, draft release notes, commit, tag, push to master, and create a GitHub release. The tag push triggers the gated PyPI publish pipeline (publish.yml); the skill surfaces the run and its approval gate.

anthony-chaudhary/dos-kernel · 59 tokens

stable-release

Promote an already-shipped rolling release (vX.Y.Z) of the DOS kernel to a named stable channel — gated on a green kernel suite + a green third-party CI run on the candidate + a clean truth syscall + a soak window. Writes an evidence file and adds a stable/ git tag on the same commit. Does NOT bump versions or build…

anthony-chaudhary/dos-kernel · 81 tokens

dos-goal-fleet

Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and dos arbitrate file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.

anthony-chaudhary/dos-kernel · 51 tokens

dos-dispatch-loop

Run recurring dos-dispatch cycles, switching to dos-replan when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.

anthony-chaudhary/dos-kernel · 49 tokens

dos-goal-gate

Ground a keep-working goal in evidence the worker did not author by wiring dos hook stop to refuse false done claims. Use for one self-stopping agent or loop worker; use dos-witness-claim for fold barriers.

anthony-chaudhary/dos-kernel · 54 tokens

dos-witness-claim

Route subagent claims through independent read-back before another agent relies on them. Use at parallel, pipeline, or synthesis barriers where shipped phases, files, rows, messages, or other effects must be witnessed.

anthony-chaudhary/dos-kernel · 47 tokens