A set of tools for checking an assistant called Wolffish, including its status, performance, memory, and past task history. It can search stored conversations and knowledge and retrieve the underlying records.

Use it to check status, search memory, read previous conversations, review task history, inspect usage, and save or correct durable knowledge.

It helps answer questions about what the assistant knows, remembers, or has done without relying on guesswork. It also provides a way to inspect health and usage information.

introspect — Skill for Claude Code and Codex by thewolffish

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 thewolffish/wolffish-app --skill introspect

Clone the repo

git clone --depth 1 https://github.com/thewolffish/wolffish-app

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thewolffish/wolffish-app/introspect/github.svg)](https://agentmods.dev/skills/thewolffish/wolffish-app/introspect)

Your own site

<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/introspect"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/introspect/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/introspect"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/introspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,089 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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.03089
Opus 5	$0.00008	$0.01545
Sonnet 5	$0.00003	$0.00618
Haiku 4.5	$0.00002	$0.00309

Measured 9d ago against content hash f562a2f1317d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

introspect 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.

The scan reads SKILL.md. This mod also ships 1 executable file (plugin/index.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/defaults/workspace/brain/cerebellum/introspect/SKILL.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Introspection

When to use

When the user asks about Wolffish's status, health, or capabilities
When the user asks what Wolffish remembers or knows
When the user asks about performance or task history
When the user asks "how are you" in a way that expects real data, not pleasantries

Tools

memory_search — THE primary retrieval tool: ranked full-text search across everything you know (conversations incl. tool outputs, episodes, knowledge, digests, tasks, feedback, usage, logs, generated files). Returns refs.
memory_get — full content behind a ref (whole episode, task transcript, knowledge file, conversation records).
conversation_list / conversation_read — enumerate past conversations and read one verbatim (messages + tool activity, paginated). conversation_read also recovers turns of the CURRENT conversation that were summarized away.
memory_save — durably save a fact to long-term knowledge (deduplicated). Append-only. To correct or forget a fact — or to amend your playbook, standing instructions, or identity — reach for the knowledge capability (knowledge_read / knowledge_edit / knowledge_forget).
usage_report — your own LLM spend (requests, tokens, cost, per model).
wolffish_recall — stable alias over the same index (query/date/source); memory_search offers richer filters.
wolffish_status — uptime, provider, capabilities, RAM, disk, index size
wolffish_performance — task counts, success rate, most used / denied tools
wolffish_memory — episode topics, knowledge file coverage, feedback counts
wolffish_list_files — structured tree of your own workspace files (~/.wolffish/workspace) with sizes. Workspace-only — not a general file browser (see Rules).

Recall vs. summary

Your context window carries a lean working set, not your whole history — everything you have ever done, said, produced, or spent lives on disk, indexed, one tool call away:

"Send me the flight plan" → memory_search query: "flight plan" → follow the ref with conversation_read or memory_get.
"What did Sana say on WhatsApp?" → memory_search — inbound channel messages are indexed too (whatsapp read-history).
"What did we do on the 18th?" → wolffish_recall with date: "2026-06-18".
"Did that World Cup task finish?" → memory_search query: "world cup", sources: "task".
"What's the file you made yesterday?" → memory_search sources: "artifact" or wolffish_list_files with dir: "files".
"What did today cost?" → usage_report.
"What was the confirmation number I gave you earlier?" (long conversation) → conversation_read on the current conversation.

Read the full file on GitHub · 321 lines

Files

What ships with it

1 file 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.

plugin/index.mjs 64 KB runs code

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.

9d ago First seen · 321 lines · 16 tokens per session scan A f562a2f1317d

Subscribe to this mod's changes

introspect is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 3,089 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 2026-08-31.

Analytics and metrics Memory and context agentic-ai debuggable extensible linux macos personal-ai

collaboration-intelligence

Maintain and use a cross-channel collaboration map of rooms, people, agents, agent owners, relationships, expertise, ownership, roster, priority/VIP handling, and recent context. Trigger when a task or message carries room/channel/sender/member metadata; the user asks who is in a room, what it is for, who owns or…

sonichi/sutando · 208 tokens

context-drop

Tiny Swift CLI that reads the focused app's text selection via the macOS Accessibility API. Sutando.app's "drop context" action (hotkey configurable via state/hotkeys.json) shells out to this binary to capture what you have highlighted.

sonichi/sutando · 0 tokens

context-reconstruct

Re-anchor on the durable record (current-track, live owner thread, pending-questions, relay, buildlog) before acting on anything that depends on earlier context. Read, do not recall.

sonichi/sutando · 43 tokens

session-recap

Reconstruct what happened in a past core session — from a high-level summary down to verbatim owner quotes — by reading the raw session transcripts (complete, crash-proof, unbiased), not the curated relay/handoff notes.

sonichi/sutando · 0 tokens

agent-computer-use

REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the agent-cu CLI commands (open, snapshot, click, type, key…

kortix-ai/agent-computer-use · 216 tokens

structured-memory

Use whenever persistent agent memory is read, written, or has grown past its budget - the first time memory is consulted in a session, whenever something worth remembering appears, and whenever MEMORY.md or a topic file exceeds its size budget. Implements a two-tier structure (slim MEMORY.md index linking memory-.md…

Hawkynt/ClaudeCodePortable · 88 tokens