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.
curl -O https://raw.githubusercontent.com/stellar-experimental/stellar-raven/main/.agents/skills/live-drift-resolution/SKILL.mdgit clone --depth 1 https://github.com/stellar-experimental/stellar-ravenWrote 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/stellar-experimental/stellar-raven/live-drift-resolution)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00109 | $0.05353 |
| Opus 5.5 | $0.00044 | $0.02141 |
| Sonnet 5.5 | $0.00022 | $0.01071 |
| Haiku 4.5 | $0.00011 | $0.00535 |
Grade A, and why
live-drift-resolution 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 24d 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live service drift resolution — stellar-raven-codemode
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.
Step 0 — read the issue, don't trust its summary
The drift issue is auto-filed by a bot. It links this runbook, lists the minimum checks before close, and gives a diffstat of the generated files. 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.
Step 1 — regenerate from live services
Run the full pipeline in this order (the daily refresh workflow runs the first four). Each step feeds the next:
node scripts/refresh-inventory.mjs # re-fetch live upstream → inventory/*.json
node scripts/build-catalog.mjs # inventory → catalog/manifest.json (+ exposure guards)
npm run micro-map:build # catalog + workflow archetypes → src/mcp/micro-map.ts
npm run spec:build # catalog → specs/super-spec.json (ships into sandbox)
node eval/plan/build-op-classes.mjs # catalog → eval/plan/op-classes.json (broad/detail/meta)
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.
- 24d ago Changed 9f85c7e1f70d
- 28d ago Changed · -63 lines 02f2c4cef079
- 1mo ago First seen · 426 lines · 109 tokens per session scan A 9dfe6b68992f
live-drift-resolution is a skill published in the GitHub repository stellar-experimental/stellar-raven (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 5,353 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ci-security-scanning-with-strix
Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…
google-agents-cli-scaffold
This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite. Covers agents-cli scaffold create, scaffold enhance, and…
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.
deploying-to-staging-environment
Use when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub Actions.
ci-debug
Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for…
devops-deployment
Use when setting up CI/CD pipelines, containerizing applications, deploying to Kubernetes, or writing infrastructure as code. DevOps & Deployment covers GitHub Actions, Docker, Helm, and Terraform patterns.