wisp-inspect

wisp-inspect is a skill for Claude Code from Samuel0101010/wisp-orchestrator. It costs 63 tokens per session (699 once invoked), scanned A, original, Apache-2.0.

A result viewer for completed WISP runs, showing the files and Git history produced by each task.

In plain words
What is it for?
Use it with a run ID to list its task branches, view the commit graph, and summarize the result branch, including branches from replanned runs.
Why use it?
It makes the output of an agent run easier to inspect without manually searching through branches.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wisp plugin — 12 skills, 1 command, 4 agents, 6 hooks shipped together

Good fit Use it with a run ID to list its task branches, view the commit graph, and summarize the result branch, including branches from replanned runs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/samuel0101010/wisp-orchestrator/wisp-inspect
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.

Any agent
npx skills add Samuel0101010/wisp-orchestrator --skill wisp-inspect
Clone the repo
git clone --depth 1 https://github.com/Samuel0101010/wisp-orchestrator

Made for: Claude Code.

Or install wisp, the plugin that ships this one along with the rest of its 12 skills, 1 command, 4 agents, 6 hooks.

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 wisp-inspect

README.md
[![agentmods](https://agentmods.dev/badge/skills/samuel0101010/wisp-orchestrator/wisp-inspect/github.svg)](https://agentmods.dev/skills/samuel0101010/wisp-orchestrator/wisp-inspect)
Your own site
<a href="https://agentmods.dev/skills/samuel0101010/wisp-orchestrator/wisp-inspect"><img src="https://agentmods.dev/badge/skills/samuel0101010/wisp-orchestrator/wisp-inspect/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 wisp-inspect

Your own site · 80×15
<a href="https://agentmods.dev/skills/samuel0101010/wisp-orchestrator/wisp-inspect"><img src="https://agentmods.dev/badge/skills/samuel0101010/wisp-orchestrator/wisp-inspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00063 $0.00699
Opus 5 $0.00032 $0.00349
Sonnet 5 $0.00013 $0.00140
Haiku 4.5 $0.00006 $0.00070

Measured 9d ago against content hash 764e84675130, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wisp-inspect 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 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.

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.

skills/wisp-inspect/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WISP — Inspect Result Branch

Show what a WISP run produced. Works on completed runs (success or failure) by inspecting the per-run git branches in the project's repo.

Platform note: git itself is cross-platform; only the grep line below has a PowerShell variant. The bash form also runs from Git Bash / WSL on Windows.

Inputs

  • runId: the run UUID. Ask the user if not provided.

Steps

  1. Resolve the runId to its repoPath:

    • If the user already supplied a repoPath (or you know it from context), skip to step 2.
    • Otherwise ask the user for the repoPath. The user almost always knows it; the API walk (run → plan → project → repoPath) is a 3-hop fallback to use only when they don't.
  2. List branches matching the runId:

    # bash
    git -C <repoPath> branch --all | grep <runId-first-8-chars>
    
    # PowerShell
    git -C <repoPath> branch --all | Select-String "<runId-first-8-chars>"
    

    Expect to see: harness/<runId>/<task1>, harness/<runId>/<task2>, ..., harness/<runId>/result (if the run succeeded). Replan runs ALSO have v2/, v3/ prefixed branches — list them too.

  3. Show the git log graph for these branches:

    git -C <repoPath> log --oneline --graph harness/<runId>/result harness/<runId>/<task-leaves...>
    

    This visualises which tasks ran in which order and where they merged.

  4. List files in the result branch:

    git -C <repoPath> ls-tree -r --name-only harness/<runId>/result
    

    Filter out node_modules and other large irrelevant trees.

  5. Per-task summary (optional, takes longer): For each task branch, show the diff against its parent:

    git -C <repoPath> log --stat -1 harness/<runId>/<taskId>
    

Errors

  • "fatal: not a git repository" → the repoPath is wrong; ask the user.
  • No branches found matching the runId → either the runId is wrong, or the run is too old (branches preserved indefinitely; should still exist).

Read the full file on GitHub · 61 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 · 61 lines · 63 tokens per session scan A 764e84675130

Subscribe to this mod's changes

wisp-inspect is a skill published in the GitHub repository Samuel0101010/wisp-orchestrator (4 stars, last pushed 5d ago), licensed Apache-2.0. It adds 63 tokens to every session and 699 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

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

deploy-steward

Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.

SethGammon/Citadel · 56 tokens

merge-review

Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.

SethGammon/Citadel · 40 tokens

pr-feedback

Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.

jjanczur/tyran · 57 tokens

upstream

Opt-in upstream contribution workflow for process improvements and field lessons. Scans the consuming repo's local AGENTS.md, {{ agentsdir }}/team.toml, and commit history for emergent rules, sanitizes sensitive client context, formats governed rule origins, and drafts an upstream Pull Request or Issue to the upstream…

NexaDuo/mARC · 83 tokens

loop-on-ci

Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

Kripu77/software-factory · 28 tokens