Open source multi agent toolkit for Claude Code and GitHub Copilot CLI: 30 agents, plan to ship workflows, review and security gates, plugin marketplace.
This repository also configures its own agents. See what ai-agents tells them →
Skill Claude Code
Load-bearing design decisions for this repo as a contract you check before changing anything. Covers the asymmetric generation seam, source-of-truth per tree, hook runtime failure policy, memory tiers, plugin surfaces, invariants, and known-weak points. Use when you say which tree is canonical, architecture contract…
Skill Claude Code
Runbook to recreate the ai-agents dev environment from scratch and survive its traps, including the uv-pinned Python 3.14.6, git hooks install, MCP layer setup, contributor commands, and PEP 668. Use when you say set up this repo, bootstrap the environment, fresh clone setup, or you hit ModuleNotFoundError yaml. Do…
Skill Claude Code
Change control for this repo. Classify a change (docs-only, investigation-only, code, plugin content, hook, workflow, ADR governance), map each class to the gates it triggers, and hold the non-negotiables with the incident behind each rule. Use when you say classify this change, what gates does this change trigger…
Skill Claude Code
Catalog of every configuration axis in this repo, env vars, commit markers, frontmatter keys, QA skip verdicts, and escape hatches, each with its enforcement point and abuse story, plus the checklist for adding a new flag safely. Use when you say what does a skip flag do, list escape hatches, can I skip this gate, add…
Skill Claude Code
Symptom-to-triage playbook for this repo's recurring failures. Blocked pushes, drift gate reds, plugin bump reds, coverage pin trips, hook exit 143, session NONCOMPLIANT. Maps each symptom to a first command, discriminating experiment, fix path, and trap. Use when you say triage this failure, why is my push blocked…
Skill Claude Code needs its repo
Runbook for this repo's documents of record. Session logs, ADRs, retrospectives, Serena memories, per-issue handoffs, plus the templates, validators, naming rules, and house prose style that bind them. Use when you say write the session log, create an ADR, fill the retro, save this to memory, which document of record.…
Skill Claude Code needs its repo
Prove-it methods for this repo. Six recipes for runtime-contract probes, guard and threshold calibration, eval A/B, docs-vs-reality audits, reproduce-on-main CI triage, and negative-control test design, each with a worked example from repo history. Use when you say probe the runtime contract, calibrate this guard…
Skill Claude Code
Operate the ai-agents generation and release machinery, covering the seven buildall.py generators, generateagents.py, the drift gates, the version-free plugin manifests, and the npm publish path. Use when you say regenerate the mirrors, run the drift checks, why is the plugin version gate red, release the npm cli. Do…
Skill Claude Code needs its repo
Execute cross-harness hook changes for Claude Code and GitHub Copilot CLI using the settled official contract, versioned probes, generators, and runtime tests. Use for run the portability campaign, port hooks to a new harness, copilot hook timeout regression, or new copilot cli release, recheck the contract. Do NOT…
Skill Claude Code
Three ranked open research programs for this repo, each with honest current-state evidence, first concrete steps, and a falsifiable milestone. Verified governance (ADR-069, proposed), cross-harness abstraction (ADR-072 proposed, ADR-068 accepted), and the self-improving loop (issue #1345). Use when you say research…
Skill Claude Code needs its repo
How a hunch becomes an accepted result in this repo. Covers the evidence bar, hypothesis-predicts-numbers discipline, and the idea lifecycle from contradiction log through probe, eval baseline, ADR debate, calibrated gate, and post-ship monitoring. Use when you say how do I prove this idea, run the idea lifecycle…
Skill Claude Code
What counts as evidence in ai-agents and how to produce it. Covers the TESTING-RIGOR pos+neg+edge bar, test layout and collection reality, coverage proof commands, runtime-contract tests with negative controls, and ADR-034 QA skip semantics at session end. Use when you say what counts as evidence, how do I test this…
Skill Claude Code
Input adapter that extracts a book's method into a structured payload and hands it off to SkillForge. Use when an operator wants to turn a methodology-bearing book (The Mom Test, Make It Stick, Influence, The Pragmatic Programmer, etc.) into one or more executable skills without hand-crafting the SkillForge prompt or…
Skill Claude Code
Populates the Forgetful knowledge base using Serena's LSP-powered symbol analysis for accurate, comprehensive codebase understanding. Use when you say "encode this repository", "populate forgetful with this codebase", "onboard to this repo", "refresh project understanding", or "build knowledge base for this project".…
Skill Claude Code
Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.
Skill Claude Code
Research external topics, create comprehensive analysis, and incorporate learnings into Serena and Forgetful memory systems. Use when you say "research and incorporate {topic}", "study {topic} and add to memory", "deep dive on {topic}", or "learn about {topic} for the project". Works on external concepts, frameworks…
Skill Claude Code
Extract learnings from a session or task through structured retrospective frameworks. Gathers evidence, runs Five Whys and fishbone diagnosis, scores atomicity, and writes a canonical retrospective artifact. Use to turn execution experience into institutional knowledge. Use when you say "run a retrospective", "retro…
Skill Claude Code
Review before merge. Stage-1 spec-compliance gate, then risk-selected Stage-2 review axes from the canonical set. analyst always runs, callers can pin extra always-on axes, and explicit deep review runs the full 16-axis set. Run after /test. Do NOT invoke code-qualities-assessment, doc-accuracy, golden-principles, or…
Skill Claude Code
Verify a review finding before acting on it. Splits a finding into verdict, diagnosis, and prescribed fix, each needing its own evidence, so you verify before you fix and check the supporting claims rather than only the conclusion. Use when you say "address this review comment", "the bot flagged this", "handle this…
Skill Claude Code
Detect infrastructure and security-critical file changes to trigger security agent review recommendations ensuring proper security oversight for sensitive modifications. Use when you ask "did I touch security-critical files", "should the security agent review this". Detection only. Do NOT use to scan source for…
Skill Claude Code
Security review knowledge delivered as parent-inline context (the form-factor counterpart to the security agent). Threat-models a code change, scores risk with CWE/CVE evidence, and returns a verdict. Use to review a diff or snippet for vulnerabilities when you want the security knowledge inline rather than dispatched…
Skill Claude Code
Detect CWE-78 (command injection) regex patterns in Python, PowerShell, Bash, and C# files before PR submission. CWE-22 is delegated to CodeQL; see Scope. Use when you ask "scan for command injection", "CWE-78 check before PR". Do NOT use to decide whether security review is warranted (use security-detection).
Skill Claude Code
Architectural analysis workflow using Serena symbols and Forgetful memory. Use when you say "analyze the architecture of this project", "map out the codebase structure", "trace dependencies for this component", "document the architecture", or "what components does this project have". Do NOT use to populate the…
Skill Claude Code
Design Service Level Objectives (SLOs) with SLIs, targets, alerting thresholds, and error budget calculations following Google SRE best practices. Use when defining reliability targets, designing SLOs, calculating error budgets, or establishing service level indicators.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: