the-pensieve

the-pensieve is a skill for Claude Code from Totes-MickGOATs/opus-pocus. It costs 139 tokens per session (1,192 once invoked), scanned A, original, MIT.

A measurement skill for checking whether instruction changes actually alter coding-agent behavior over a week. It counts events such as repeated advisories, review rounds, agent handoffs, injected tokens, and session results.

In plain words
What is it for?
Use it after changing agent instructions to measure repeated warnings, review depth, incomplete-work handoffs, prompt overhead, wrong-agent assignments, and outcomes.
Why use it?
It replaces subjective audits with observed numbers, helping you see whether a change improved the workflow or merely repeated the same reasoning.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the opus-pocus plugin — 21 skills, 1 agent shipped together

Good fit Use it after changing agent instructions to measure repeated warnings, review depth, incomplete-work handoffs, prompt overhead, wrong-agent assignments, and outcomes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/totes-mickgoats/opus-pocus/the-pensieve
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 Totes-MickGOATs/opus-pocus --skill the-pensieve
Clone the repo
git clone --depth 1 https://github.com/Totes-MickGOATs/opus-pocus

Made for: Claude Code.

Or install opus-pocus, the plugin that ships this one along with the rest of its 21 skills, 1 agent.

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 the-pensieve

README.md
[![agentmods](https://agentmods.dev/badge/skills/totes-mickgoats/opus-pocus/the-pensieve/github.svg)](https://agentmods.dev/skills/totes-mickgoats/opus-pocus/the-pensieve)
Your own site
<a href="https://agentmods.dev/skills/totes-mickgoats/opus-pocus/the-pensieve"><img src="https://agentmods.dev/badge/skills/totes-mickgoats/opus-pocus/the-pensieve/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 the-pensieve

Your own site · 80×15
<a href="https://agentmods.dev/skills/totes-mickgoats/opus-pocus/the-pensieve"><img src="https://agentmods.dev/badge/skills/totes-mickgoats/opus-pocus/the-pensieve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,192 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 $0.00139 $0.01192
Opus 5 $0.00069 $0.00596
Sonnet 5 $0.00028 $0.00238
Haiku 4.5 $0.00014 $0.00119

Measured 12d ago against content hash efe61a756593, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

the-pensieve 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/the-pensieve/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔮 The Pensieve

"A week of numbers in the basin. Vibes are not telemetry."

Every other spell changes the instruction layer. This one finds out whether the changes worked. The alternative — another audit — just re-applies the same judgment that wrote the instructions; only behavior counts.

The counters

Instrument what the spells claim to improve. Core set:

Counter Needs What it validates Source
Stop/advisory re-fires per session — same advisory, unchanged state hooks + transcripts Finite Recursum's fingerprint fixes Hook logs, or grep transcripts for the advisory headers
Review-loop rounds per task — review→fix→re-review depth transcripts Loop caps working Transcripts / task logs
Subagent bounces per branch — how often incomplete work goes back agents Definition-of-done clarity Dispatch logs, PR/branch history
Tokens injected per prompt by hooks hooks Muffliato Hookus Instrument emitters to log output bytes; or measure injected blocks in transcripts
Wrong-agent routings — dispatched then redirected agents + transcripts Descriptio Reducio Transcripts: dispatches followed by a different agent doing the work
Rule citations of stale facts — model quotes something no longer true none Obliviate Fossilium Review of session outputs; user corrections
User corrections per session — times the human had to redirect transcripts Everything Transcripts: user messages contradicting the previous assistant turn
Session outcome — task done / partial / abandoned none The bottom line End-of-session state

Add repo-specific counters for whatever the audit flagged worst — measure where the disease was.

Read the Needs column before promising anything. A repo with no hooks cannot measure advisory re-fires or injected tokens; a repo with no subagents cannot measure bounces or wrong routings. Five of these eight have a prerequisite most small repos do not meet.

Read the full file on GitHub · 75 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. 12d ago First seen · 75 lines · 139 tokens per session scan A efe61a756593

Subscribe to this mod's changes

the-pensieve is a skill published in the GitHub repository Totes-MickGOATs/opus-pocus (10 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 1,192 once invoked, about $0.0007 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

claude-md-architect

Design, create, extract, or audit CLAUDE.md files and their supporting docs/ folder structure for Claude Code projects. Use this skill whenever the user asks to create a new CLAUDE.md, extract context from a long session into a CLAUDE.md system, audit/refactor an existing CLAUDE.md that has bloated, review whether…

trin-zenityx/claude-md-architect · 210 tokens

mle-workflow

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

affaan-m/ECC · 44 tokens

react-patterns

React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.

affaan-m/ECC · 49 tokens

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

huggingface-llm-trainer

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

waybarrios/opencode-power-pack · 65 tokens

feature-dev

Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…

waybarrios/opencode-power-pack · 62 tokens