pinot-janitor

pinot-janitor is a skill for Claude Code, Codex from jbstavers/pinot-pi. It costs 29 tokens per session (771 once invoked), scanned A, original, MIT.

A specialist workflow for closing out Pinot implementations, updating project documentation, or classifying limited cleanup. Pinot is the project environment this workflow is designed to maintain.

In plain words
What is it for?
Finishing Pinot-related implementation work, maintaining its documentation, and deciding how bounded cleanup should be handled.
Why use it?
It protects active work and files whose status is uncertain while enforcing required project checks and a single writer. This reduces the risk of cleanup overwriting ongoing implementation work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Finishing Pinot-related implementation work, maintaining its documentation, and deciding how bounded cleanup should be handled.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jbstavers/pinot-pi/pinot-janitor
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 jbstavers/pinot-pi --skill pinot-janitor
Clone the repo
git clone --depth 1 https://github.com/jbstavers/pinot-pi

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 pinot-janitor

README.md
[![agentmods](https://agentmods.dev/badge/skills/jbstavers/pinot-pi/pinot-janitor/github.svg)](https://agentmods.dev/skills/jbstavers/pinot-pi/pinot-janitor)
Your own site
<a href="https://agentmods.dev/skills/jbstavers/pinot-pi/pinot-janitor"><img src="https://agentmods.dev/badge/skills/jbstavers/pinot-pi/pinot-janitor/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 pinot-janitor

Your own site · 80×15
<a href="https://agentmods.dev/skills/jbstavers/pinot-pi/pinot-janitor"><img src="https://agentmods.dev/badge/skills/jbstavers/pinot-pi/pinot-janitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 771 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 $0.00029 $0.00771
Opus 5 $0.00015 $0.00385
Sonnet 5 $0.00006 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 12d ago against content hash 80c85f7f5b66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pinot-janitor 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 12d 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/pinot-janitor/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pinot Janitor

You are a specialist editing child, not a generic root agent. Read this skill and the relevant relative references before inspecting the project. The coordinator must supply the exact project scope, handoff paths, configured history-root exception, provenance, and active-work exclusions. Do not delegate or commit.

Herdr prerequisite

Every Janitor run is a durable workflow. Start through pinot_native_herdr_implementer with the start-only janitor profile and explicit package skill loading; later lifecycle actions must recover and verify its immutable profile metadata. Before inspection or writing, require the active Herdr environment, Pi integration, supported Herdr version, matching project attachment, and configured exact built-in model. If a prerequisite is unavailable, stop with a direct setup message. Never fall back to root editing, a temporary worker, or an unverified host.

Keep one writer total. Do not write while another writer is active. The Janitor specialist is the sole writer during this assignment. Use the supplied handoff as the map; current implementation and Git state outrank aspirational prose. Do not reconstruct provenance from transcripts.

Modes

  • closeout: consume the exact implementation handoff, spot-check named paths and Git state, update supported durable documentation, maintain the semantic history entry when the exact configured history root is supplied, and classify project-local ephemeral artifacts.
  • docs: review durable project documentation against current behavior and conventions. Do not change product behavior to make prose agree.
  • sweep: make a bounded inventory and classify every candidate as delete, retain, or unresolved; retain uncertainty.

For closeout, stop if the handoff or exact history-root exception is absent or stale. Never infer authority over another repository.

Operating contract

  1. Read the supplied project instructions and exact handoff first. Inspect status and named paths before editing.
  2. Edit only assigned project documentation and high-confidence project-local ephemeral artifacts, plus the exact history-root exception. Do not alter source behavior.
  3. Preserve semantic provenance: root and durable-child identity, checkpoints as references only, bounded background purposes/dispositions, commit range, review dispositions, verification, deviations, documentation impact, and remaining work.
  4. History is append-only. Check the intended dated directory, index line, and every snapshot filename before writing. Stop on collision or ambiguity; never overwrite or invent a suffix.
  5. Copy only safe exact specification and plan snapshots supplied by the coordinator. Name the primary plan plan.md and additional plans with supplied deterministic descriptive slugs. Do not concatenate plans.
  6. Never copy transcripts, checkpoint bodies, credentials, authentication state, sessions, generated diagnostic output, or uncertain inputs.
  7. For cleanup, use only delete, retain, or unresolved. Delete only understood, reproducible, inactive, ignored project-local ephemeral output. Never delete tracked source/tests, active work, human input, application data, sessions, checkpoints, caches, backups, or application logs.
  8. Distinguish permanent application logs/configuration from temporary diagnostic/test logs when documenting a project. Verify locations, retention, configuration, and privacy boundaries only when logging applies.

Read the full file on GitHub · 39 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 39 lines · 29 tokens per session scan A 80c85f7f5b66

Subscribe to this mod's changes

pinot-janitor is a skill published in the GitHub repository jbstavers/pinot-pi (11 stars, last pushed 27d ago), licensed MIT. It adds 29 tokens to every session and 771 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens

magpie-security-issue-import-from-md

Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.

apache/magpie · 73 tokens