Plugin Claude Code
Companion plugin marketplace for Agentic Atlas — field-tested patterns for designing agent systems, readable by people and consultable by agents over MCP at agentic-atlas.dev.
3 yesterday A
tokens not measured
Plugin Claude Code
Do design work with Agentic Atlas over hosted MCP at agentic-atlas.dev/mcp/. Three skills — audit an existing agent artifact, design a new agent system, apply one named pattern — over two read-only agents; no SDK, CLI, local server, or content bundle is installed.
3 yesterday A
tokens not measured
MCP server Claude CodeCodexCursor +2
MCP server "agentic-atlas", hosted remotely at agentic-atlas.dev, as configured in aj604/agentic-atlas-plugin.
3 yesterday A
tokens not measured
Instructions file CodexOpenCode
AGENTS.md instructions for aj604/agentic-atlas-plugin, covering agents.md — working on the agentic atlas companion plugin, what this repository is, the patterns are not in this tree, layout and conventions to keep.
3 yesterday A 909 tokens
Agent
Reads a user's agent artifact (skill, agent definition, plugin, hooks, or multi-agent workflow) strictly read-only and consults the published agentic-atlas corpus, returning either a cited audit of the artifact against the patterns or a cited edit plan for applying one named pattern. Two modes selected by the dispatch…
3 yesterday A 92 tokens
Agent
Explores the published agentic-atlas pattern corpus for a stated design problem and returns a distilled, situation-specific consultation — which patterns apply, what each prescribes or warns for this design, tensions between them, and fetchable citations for deeper reading. Pure corpus traversal, no file access.…
3 yesterday A 79 tokens
Skill Claude CodeCodex
Turn one named Agentic Atlas pattern into concrete, cited edits to one existing artifact. Use whenever the user names a specific atlas pattern — by id, by title, or by pointing at a page on agentic-atlas.dev — and wants it applied, adopted, retrofitted, or implemented in their skill, agent definition, plugin, or…
3 yesterday A 155 tokens
Skill Claude CodeCodex
Design a new agent system with the published Agentic Atlas patterns — interview the user, consult the corpus once with the consolidated problem, and propose a decomposition where every structural choice carries its citation. Use whenever the user is starting a skill, subagent, agent definition, plugin, hook set, or…
3 yesterday A 206 tokens
Skill Claude CodeCodex
Audit an existing agent artifact against the published Agentic Atlas patterns (agentic-atlas.dev) — a skill, subagent or agent definition, plugin, hook configuration, or multi-agent workflow — returning cited, checkable findings. Use whenever the user asks to review, audit, critique, sanity-check, or grade an agent…
3 yesterday A 175 tokens
toolshed
10Plugin Claude Code
A personal Claude Code plugin marketplace. Ships doc-lifecycle: stop agents from acting on stale docs — evidence-backed drift detection, surgical fixes.
2 25d ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
Instructions for aj604/toolshed, a project described as: Reference docs as checkable claims — a Claude Code plugin for the documentation lifecycle: bootstrap → write → detect drift → fix.
2 25d ago A 4 tokens
copy · 100% MIT
Instructions file
Instructions for aj604/toolshed, covering claude.md, layout (pointers, not descriptions), working on the plugin, conventions and gotchas.
2 25d ago A 6,400 tokens
original MIT
domain
13Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
2 25d ago A 0 tokens
copy · 75% MIT
Agent
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
2 25d ago A 0 tokens
copy · 91% MIT
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
2 25d ago A 0 tokens
copy · 81% MIT
Plugin Claude Code
Stop agents from acting on stale docs. Write README/CLAUDE.md/runbooks as checkable claims, grow the doc set only on demand signals, audit against the code with evidence-backed verdicts, and land fixes surgically — bootstrap → write → grow → detect → fix → prune/distill → schedule.
2 25d ago A
tokens not measured
original MIT
Agent
Authors the durable residue of one approved DISTILL record - per-section insight walk, code-verified claims, one decision-log entry - and returns it as edit-plan operations (the residue's create-document plus the artifact's retire-document and any in-artifact edits) for the applier to execute. Writes no files and…
2 25d ago A 83 tokens
original MIT
Agent
Converts documentation to dense, LLM/agent-optimized form, or authors agent-facing docs from a source doc, findings, or a repo. Maximizes signal-per-token while refusing to assert anything it has not verified. Dispatch for whole-doc or verification-heavy agent-facing jobs; one-line tweaks are handled inline by the…
2 25d ago A 75 tokens
original MIT
Skill Claude CodeCodex
Use when a repo has no doc set yet (or a bare one) and you need to create the baseline from scratch — "document this project" / "add docs" / "set up documentation" — producing the smallest high-leverage doc set and deliberately stopping, instead of cataloguing everything. This is the whole-repo…
2 25d ago A 125 tokens
original MIT
Skill Claude CodeCodex
Use when auditing documentation for low-value content — redundant, verbose, duplicated, or past its useful form — proposing pruning/condensing/distillation, and whenever bloat analysis runs programmatically (nightly sweep, PR gate, or a chunk-executor invocation handed its chunk slice) and must emit a structured…
2 25d ago A 87 tokens
original MIT
Skill Claude CodeCodex
Use when auditing documentation against the code it describes, checking whether a README/CLAUDE.md/runbook is still accurate, or finding which doc passages a code change invalidates — and whenever drift detection is invoked programmatically (by a PR check or nightly sync) and must emit a structured, parseable result.
2 25d ago A 69 tokens
original MIT
fixing-docs
22Skill Claude CodeCodex
Use when landing fixes from a doc-lifecycle audit report — applying approved drift records (STALE, UNVERIFIABLE) or bloat records (CUT, CONDENSE, EXTRACT-AND-MOVE, MERGE-DOC, RETIRE-DOC, DISTILL) to the documentation, and whenever tempted to hand-edit a document because a record, a record-ID list, an issue comment, or…
2 25d ago A 97 tokens
original MIT
growing-docs
23Skill Claude CodeCodex
Use when a repo already has baseline docs but a demand signal says they are no longer enough — the same question answered twice, a fact re-derived the hard way across sessions, an incident with no runbook, onboarding pain, a recurring "why is it like this?", someone asking "should we document X?", or a…
2 25d ago A 140 tokens
original MIT
Skill Claude CodeCodex
Use when wiring a repo for automated/unattended documentation audit — "set up doc sync", "automate drift detection", "schedule nightly doc checks", "keep docs in sync automatically" — installs the doc-lifecycle GitHub Actions (scheduled read-only drift and bloat audits, an optional policy apply lane, a manual apply…
2 25d ago A 96 tokens
original MIT