stellar-raven: Skill for Claude Code

.agents/skills/live-drift-resolution/SKILL.md

live-drift-resolution is a skill for Claude Code, Codex from stellar-experimental/stellar-raven. It costs 109 tokens per session (6,255 once invoked), scanned A, original, Apache-2.0.

A runbook for resolving differences between a committed catalog and the live upstream services it represents. A catalog is a stored list of available services, operations, and related rules.

In plain words
What is it for?
Use it when daily checks report live service drift, to regenerate artifacts, classify the change, and update policy or routing baselines when needed.
Why use it?
It helps determine whether the difference is a routine update or a change that affects what the system exposes or how it routes requests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is stellar-experimental/stellar-raven's own configuration. It tells Claude Code and Codex how to work on stellar-raven itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stellar-raven configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/refresh-inventory.mjs # re-fetch live upstream → inventory/*.json.

Reuse

Borrowing it

Nothing to install: this file belongs to stellar-experimental/stellar-raven. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/stellar-experimental/stellar-raven/main/.agents/skills/live-drift-resolution/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/stellar-experimental/stellar-raven

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for live-drift-resolution

README.md
[![agentmods](https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/live-drift-resolution/github.svg)](https://agentmods.dev/skills/stellar-experimental/stellar-raven/live-drift-resolution)
Your own site
<a href="https://agentmods.dev/skills/stellar-experimental/stellar-raven/live-drift-resolution"><img src="https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/live-drift-resolution/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.

agentmods 80×15 button for live-drift-resolution

Your own site · 80×15
<a href="https://agentmods.dev/skills/stellar-experimental/stellar-raven/live-drift-resolution"><img src="https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/live-drift-resolution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,255 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00109 $0.06255
Opus 5 $0.00055 $0.03127
Sonnet 5 $0.00022 $0.01251
Haiku 4.5 $0.00011 $0.00626

Measured 9d ago against content hash 9dfe6b68992f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

live-drift-resolution scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

> const cp=require("child_process");
.agents/skills/live-drift-resolution/SKILL.md · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live service drift resolution — stellar-raven-codemode

This skill is agent-agnostic: a plain-markdown runbook. Claude Code invokes it as a skill; Codex or any other CLI agent can be pointed at this file directly.

Boundary: this resolves live service surface drift. If the user asks whether repo truth is current across evals, golden answers, improvements, upstream issues, or PRs, use truth-maintenance as the coordinator and this skill as only the drift lane.

North star

The committed catalog (catalog/manifest.json, inventory/*.json, specs/super-spec.json, eval/plan/op-classes.json) is a frozen snapshot of upstream surfaces that drift on their own schedule. A daily CI job re-fetches the live surfaces and files a "Live service drift detected" issue when the snapshot no longer matches. Resolving it is mechanical regeneration plus one real judgment:

Is this a clean mechanical bump (absorb and commit), or does it change the exposed surface or the routing behavior (which needs a policy or baseline decision in the SAME change)?

Getting that judgment wrong in either direction is the failure mode: rubber-stamping a bump that added a callable operation ships an unvetted surface; re-baselining a gate for a bump that didn't touch routing hides a real regression behind a moved goalpost. The whole skill exists to make that one call correctly and prove it.

Bindings that change (which CI repo, which secret store) live in AGENTS.md, especially Coordination and Hard rules, not here. This runbook is the procedure.

Step 0 — read the issue, don't trust its summary

The drift issue is auto-filed by a bot and includes a diffstat and the exact regen commands. Read it for the shape (which files, roughly how big), but treat its framing as a starting point, not a verdict — the whole point of the steps below is to derive the truth from the actual diff.

Read the full file on GitHub · 426 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. 9d ago First seen · 426 lines · 109 tokens per session scan A 9dfe6b68992f

Subscribe to this mod's changes

live-drift-resolution is a skill published in the GitHub repository stellar-experimental/stellar-raven (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 6,255 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.