Agent Native

codeprobe-check-infra

This skill diagnoses whether mined task directories can run safely by checking for capability drift and verifying credential time-to-live against expected…

by SourcegraphOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (sourcegraph)

Agents
Claude Code
License
Apache-2.0 (permissive)
Pin
349658apinned Oct 9, 2026
Context cost
about 970 tokenswhen the skill loads
GitHub stars
2on sourcegraph/codeprobe
Scripts
None found

What it does

“Diagnose mined-task infrastructure for drift and offline readiness. Compares metadata.json capability snapshots to live capabilities and runs credential-TTL preflight for airgapped runs. Triggers on check infra, capability drift, preamble drift, offline preflight, credential ttl, airgapped run readiness. Use this before running mined tasks that were produced on a different machine or weeks ago.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill diagnoses whether mined task directories can run safely by checking for capability drift and verifying credential time-to-live against expected offline runtime. It compares saved metadata snapshots to current live capabilities and preflight-checks credential expiration before airgapped execution.

When to use it

  • Before running mined tasks from different machines or old checkpoints
  • Validating offline run viability with credential TTL constraints
  • Detecting unintended capability changes in task environments
  • Pre-flight checks before executing airgapped or disconnected runs

When not to

  • When deploying to new environments where drift is expected and acceptable
  • If credentials are not time-limited or offline execution is not planned

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add sourcegraph/codeprobe --skill codeprobe-check-infra

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install sourcegraph/codeprobe codeprobe-check-infra@349658a0c14622dccccc9be038cabca63a1e4a0b

Installs the commit we checked (349658a).

Copy by hand

Download the folder at 349658a and put it in .claude/skills/codeprobe-check-infra for Claude Code and in .agents/skills/codeprobe-check-infra for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 349658a

Claude Code plugin

/plugin install sourcegraph@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "codeprobe-check-infra" by Sourcegraph.

Source, pinned to commit 349658a0c14622dccccc9be038cabca63a1e4a0b:
https://github.com/sourcegraph/codeprobe/tree/349658a0c14622dccccc9be038cabca63a1e4a0b/src/codeprobe/skills_data/codeprobe-check-infra

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/codeprobe-check-infra/ for Claude Code and .agents/skills/codeprobe-check-infra/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/sourcegraph/codeprobe-check-infra

SKILL.md at the pin

---
name: codeprobe-check-infra
description: Diagnose mined-task infrastructure for drift and offline readiness. Compares metadata.json capability snapshots to live capabilities and runs credential-TTL preflight for airgapped runs. Triggers on check infra, capability drift, preamble drift, offline preflight, credential ttl, airgapped run readiness. Use this before running mined tasks that were produced on a different machine or weeks ago.
user-invocable: false
---

# codeprobe check-infra (autonomous agent contract)

Pre-run diagnostics for mined task directories and airgapped environments.
Splits into two primary subcommands: `drift` (capability snapshot vs live) and
`offline` (credential TTL vs expected run duration).

## Environment (pre-loaded)

- !`codeprobe doctor --json`
- !`codeprobe check-infra offline --json`

`doctor` gives the overall readiness state; `check-infra offline --json`
pre-warms the credential-TTL surface so the agent can decide up front whether
an offline run is viable. If the offline envelope reports `ok: false` with
`error.code` of `OFFLINE_PREFLIGHT_FAILED`, do NOT attempt an offline run
before resolving.

## Bare invocation

Capability drift against a specific task directory:

```bash
codeprobe check-infra drift <task_dir> --json
```

Tolerate drift (emit warning instead of failing):

```bash
codeprobe check-infra drift <task_dir> --json --allow-capability-drift
```

Offline credential preflight for an anticipated 2-hour run:

```bash
codeprobe check-infra offline --json --expected-run-duration 2h
```

Restrict the offline check to a single backend:

```bash
codeprobe check-infra offline --json --backend claude
```

## JSON fields to parse

Top-level keys are exactly the envelope fields shown below. Parse `ok`; on
`false` inspect `error.code` (`error` is a single object, never an array).

Drift:

```json
{
  "record_type": "envelope",
  "ok": true,
  "command": "check-infra drift",
  "version": "<codeprobe version>",
  "schema_version": "1",
  "exit_code": 0,
  "data": {
    "command_schema_version": "1",
    "task_dir": "<abs-path>",
    "has_drift": false,
    "snapshot_count": 4,
    "live_count": 4,
    "added": [ "..." ],
    "removed": [ "..." ]
  },
  "error": null,
  "warnings": [],
  "next_steps": []
}
```

Detected drift without `--allow-capability-drift` surfaces as `ok: false`
with `error.code` of `CAPABILITY_DRIFT`, not as a `data` field.

Offline:

```json
{
  "record_type": "envelope",
  "ok": true,
  "command": "check-infra offline",
  "version": "<codeprobe version>",
  "schema_version": "1",
  "exit_code": 0,
  "data": {
    "command_schema_version": "1",
    "expected_run_duration": "2h",
    "backend_filter": [ "claude" ]
  },
  "error": null,
  "warnings": [],
  "next_steps": []
}
```

A TTL shortfall surfaces as `ok: false` with `error.code` of
`OFFLINE_PREFLIGHT_FAILED`; the per-backend TTL detail rides on
`error.detail`.

## Error handling

Only the codes below may surface. At runtime the envelope's `error` object
carries the authoritative message and remediation for whichever code fired.

| Code | Kind | Retryable? | Action |
|---|---|---|---|
| CAPABILITY_DRIFT | diagnostic | no | Run `codeprobe doctor --capabilities`; re-mine or re-baseline if intentional. |
| METADATA_MISSING | diagnostic | no | Target task_dir has no metadata.json; stop. |
| OFFLINE_PREFLIGHT_FAILED | diagnostic | no | At least one backend's credential TTL is too short; rotate/refresh credentials. |
| OFFLINE_NET_ATTEMPT | diagnostic | no | Component attempted network IO while offline; fix config. |
| STALE_USER_HOME_SKILL | diagnostic | yes (with fix) | Re-install the referenced skill bundle per remediation. |
| DOCTOR_CHECKS_FAILED | diagnostic | no | Cross-surfaced from doctor; resolve those checks first. |
| INTERRUPTED | diagnostic | **TERMINAL — do not retry** | Signal halted the command; stop. |

## Retry policy

- Maximum retry depth per error chain: **2**. After two consecutive errors
  sharing the same code, stop and surface the envelope to the caller.
- Terminal errors (INTERRUPTED) are **never** retried.
- Drift errors almost always need a human decision (re-mine vs accept-drift).
  Do not auto-retry with `--allow-capability-drift` unless the caller asked
  for it — that flag changes semantics, not transient state.

From sourcegraph/codeprobe at 349658a, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at 349658a

Files

1 file, 4.3 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 349658a
All 7 skills from Sourcegraph

More from Sourcegraph

  • searching-sourcegraph

    This skill enables agents to search and navigate codebases using Sourcegraph, with guided workflows for finding implementations, understanding systems…

    Claude Code, Codex, Cursor +4 · about 2.2K tokens · pinned 6 days ago

  • codeprobe-calibrate

    This skill runs a validation gate for a curator version by comparing it against a holdout dataset and a reference curator.

    Claude Code · about 870 tokens · pinned 6 days ago

  • codeprobe-interpret

    This skill analyzes results from codeprobe benchmark runs by comparing configurations, computing statistical rankings, and generating actionable…

    Claude Code · about 920 tokens · pinned 6 days ago

  • codeprobe-mine

    Extracts reusable eval tasks from a repository's merge history using the codeprobe CLI.

    Claude Code · about 1.6K tokens · pinned 6 days ago

  • codeprobe-run

    Execute eval task suites against an AI coding agent using codeprobe, spawning isolated sessions and scoring each task with automated tests.

    Claude Code · about 1.5K tokens · pinned 6 days ago

  • sourcegraph-nav

    Navigates code using Sourcegraph to locate where symbols are defined and find all places they are used.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 580 tokens · pinned 6 days ago

All Cloud and DevOps skills
  • n8n-cli

    This skill enables agents to manage n8n workflows, credentials, executions, and instance resources via the n8n CLI command-line tool.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +4 · about 2.9K tokens · pinned 6 days ago

  • managing-streamlit-apps

    Manage Streamlit apps running in PostHog sandboxes through the full lifecycle: create, set or edit source code, start and stop the sandbox, poll status, and…

    by PostHogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 1.4K tokens · pinned 6 days ago

  • release-candidate-prep

    Prepares a local Python SDK release candidate in a dedicated Git worktree when explicitly invoked with a version number.

    by OpenAIOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 4.8K tokens · pinned 6 days ago

  • cloud-run-basics

    Deploys and manages Google Cloud Run services, jobs, and worker pools for running containerized applications or source code.

    by GoogleOfficial publisher

    Claude Code, Codex, Cursor +4 · about 3.9K tokens · pinned 6 days ago

  • debug-openshell-cluster

    Diagnoses OpenShell gateway deployment problems across Docker, Podman, Kubernetes, and VM compute platforms.

    by NVIDIAOfficial publisher

    Claude Code, Codex, Cursor +4 · about 19.1K tokens · pinned 6 days ago

  • hf-cloud-aws-context-discovery

    This skill reads the user's local AWS configuration to discover their active profile, region, account ID, and caller identity before any AWS work begins.

    by Hugging FaceOfficial publisher

    Claude Code, Codex, Cursor +4 · about 830 tokens · pinned 6 days ago

Open roles at Sourcegraph

2 open roles on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use