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 agentmods add skills/sponge-b0b/polaris/codegraphnpx skills add sponge-b0b/Polaris --skill codegraphgit clone --depth 1 https://github.com/sponge-b0b/PolarisWhat 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 | $0.00059 | $0.00698 |
| Opus 5 | $0.00030 | $0.00349 |
| Sonnet 5 | $0.00012 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
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.
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 statusto 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.
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.
- 2d ago First seen · 54 lines · 59 tokens per session scan A cbca3b84af68
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.
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.
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…
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.
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.
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.
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.