knowledge-management agents

boykush/scraps

Agent

Part of llm-wiki

Map a natural-language wiki-health request to one or more scraps lint rules, run them, interpret each violation as a signal against the user's purpose, and either apply mechanical fixes or report findings. Use this agent for purpose-driven Scraps lint work.

boykush/scraps

Agent

Part of llm-wiki

Provide the default LLM Wiki schema for Scraps, grounded in the official Scraps docs and inspired by Andrej Karpathy's LLM Wiki pattern. Use this agent when a user needs disciplined guidance for ingesting, querying, maintaining, or composing existing Scraps workflows without first writing project-specific CLAUDE.md or…

mycelium-hq/ai-brain-starter

Agent

Part of ai-brain-starter

Decomposes a task into a concrete, ordered implementation plan. Use BEFORE any code is written for non-trivial work. Read-only by construction — it cannot edit files, so it can never "just fix it" and skip the plan.

mycelium-hq/ai-brain-starter

Agent

Part of ai-brain-starter

Implements a planned change — edits files, runs commands, makes tests pass. The only agent with write authority. Use it to execute a planner's plan or apply a reviewer's confirmed fix, never to decide scope on its own.

mycelium-hq/ai-brain-starter

Agent

Part of ai-brain-starter

Reviews a change for correctness, security, and convention adherence. Use AFTER a resolver edit and BEFORE merge. Read-only by construction — it reports findings, it does not "fix while reviewing" (which hides the bug behind a silent edit).

pumblus/okf-harness

Agent

Issues and PRDs live as GitHub issues; use the gh CLI for all operations.

pumblus/okf-harness

Agent

Each item names the material and the branch that triggers reading it.

pumblus/okf-harness

Agent

Use only when preparing, validating, or writing up a public OKF Harness release. Owns operational release proof and the release notes template.

pjt222/agent-almanac

Agent

Part of agent-almanac

Knowledge organization and library management specialist for cataloging, classification, collection curation, material preservation, and information retrieval.

ractive/hyalo

Agent Claude Code

Use this agent when a task involves implementing, modifying, or reviewing Rust code that requires language-specific expertise, including ownership and borrowing, lifetimes, traits and generics, async/concurrency correctness, error handling, performance optimization, Cargo workspace management, or unsafe code. Do not…

ractive/hyalo

Agent Claude Code

Use this agent when a task involves designing, implementing, debugging, or maintaining CI/CD pipelines for Rust projects on GitHub Actions, including multi-platform builds for Linux, macOS, and Windows, release workflows, artifact publishing, Homebrew packaging, and Linux distribution packages such as deb or rpm. Do…

modeled-information-format/mnemonic

Agent

Part of mnemonic

Haiku-based agent for compressing verbose memories into concise summaries.

modeled-information-format/mnemonic

Agent

Part of mnemonic

Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.

modeled-information-format/mnemonic

Agent

Part of mnemonic

Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.

mishalyalin/pupsik

Agent

You are the Architect. Your job is to design the plan before anyone writes code or moves files.

mishalyalin/pupsik

Agent

You are the Discoverer. Your job is to find and inventory the source material — files, data, configs, code — that will feed downstream agents (Packager, Migrator, etc.).

mishalyalin/pupsik

Agent

You are the Packager. Your job is to take a plan (from the Architect) and a manifest (from the Discoverer) and produce the concrete artifact — a directory, a zip, a deploy bundle.

superuser-pal/awesome-second-brain

Agent Claude Code

Aggregate performance review material from the vault for a given period. Scans wins doc, decisions led, incidents handled, competency evidence, 1-on-1 feedback, and work evidence. Invoke via /brief or when the user asks for review prep.

superuser-pal/awesome-second-brain

Agent Claude Code

Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident reconstruction, evidence gathering, or any situation requiring full Slack context.

superuser-pal/awesome-second-brain

Agent Claude Code

Classify, transform, and migrate vault content from a source vault into this PAL Second Brain vault. Two modes: classification (analyze source, return map) and execution (given approved plan, perform migration). Invoked by /upgrade.

chrono-meta/forge-harness

Agent

Part of fh-commons

Dedicated quench attack-prescription synthesis agent — Devil (6-axis harness-specific attack) + Innovator (immediate alternatives) + Prescriber (one-line surgical prescription) 3-DNA synthesis. Every attack is paired with a concrete fix direction — no pure criticism. Built-in replacement engine for steel-quench Wave…

chrono-meta/forge-harness

Agent

Part of fh-meta

Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…

chrono-meta/forge-harness

Agent

Part of fh-meta

Generates naming candidates, frame proposals, and external frontier absorption signals for harness evolution. Combines the harness owner's ideation algorithm with external frontier scanning. Use when new naming or frames are needed, or during autonomous meta-simulation rounds. Supports environments without naming…

AdrianV101/obsidian-pkm-plugin

Agent

Part of vault-pkm

Use proactively in the background after creating or modifying multiple vault notes, or when asked about vault link health. Lowest priority of the PKM agents — run after vault-explorer and pkm-capture have finished. Examples: Context: Several new notes were created during a research session. user: "OK I think we've…