agent-plugins

A marketplace of 25 plugins for Claude Code that also work with any coding agent (Codex, Cursor, Gemini, …) through standard SKILL.md + AGENTS.md entry points. Every plugin is gated by evals; 15 of them have a published before/after example with the models disclosed; 12 are graded by a model in CI on every change.

Claude Code
/plugin marketplace add JRichlen/agent-plugins
/plugin install <name>@jrichlen
Any harness, via APM (pin the SHA)
apm install JRichlen/agent-plugins/plugins/<name>#<sha>

Three ways in

Evidence

Before & after examples

One real prompt per skill, answered with and without it. Verdict first, transcripts on demand, every model named by role, and a verification path back to the CI run that produced the pair.

Story

Design trajectory

How this marketplace became what it is, told as the decisions that shaped it: what forced each one, what was rejected, and a receipt you can check. Start here for the why behind everything else.

Reference

How every change is checked

The full inventory of eval tiers, what each proves and what it structurally cannot, when it fires and what it costs — the doc the cheap tier itself keeps in sync with the workflows.

Deep dives 2 plugins with a long-form page

Deep dive

agent-compiler

Compile deterministic, content-hashed agents from small behavior modules: fuzzy intent becomes a typed AgentQuery, a stdlib-only kernel resolves modules and fails closed on conflicts, and out comes an immutable AgentImage with per-line provenance.

Deep dive

redgate

The Red Gate protocol: rounds of ARM → TRACE → JUDGE with graduated autonomy, a verifier proven able to fail before any work starts, and PATCH / MINOR / MAJOR gates so irreversible decisions always block on a human.

All plugins

  1. agent-compiler v0.3.0

    stronggraded in CI

    Compile deterministic, content-hashed agents from small behavior modules: a skill turns fuzzy intent into a typed AgentQuery, a stdlib-only kernel resolves modules, expands dependencies, fails closed on conflicts and over-ceiling effects, and emits an immutable AgentImage plus a rendered harness-native subagent — never inventing behavior text without provenance.

  2. codebase-design v1.0.0

    subtlecheap tier only

    Before writing a new interface (module boundary, class API, function signature, or service contract) that at least two call sites will depend on, that crosses a module/service/team/persistence boundary, or that will be expensive to change later — produce 3+ radically different candidate designs and compare them on depth, locality, and seam placement before picking one. Use on "before committing to an interface", "design this API/module/class boundary", "how should this be structured", "compare interface designs", "is this the right abstraction", "design it twice", reviewing a proposed interface shape in a PR — or self-trigger whenever about to write a new interface meeting that bar.

  3. context-handoff v1.0.0

    moderatecheap tier only

    Walk the ordered continue, clear, handoff, delegate, compact decision tree at a phase boundary, and keep any handoff artifact pointer-only — settled specs, plans, ADRs, issues, commits, and diffs referenced by path or URL, never copied inline. Use this when the context window is getting full, you're wondering whether to clear or compact, you need to hand off to another harness, directory, or colleague, you've hit a phase boundary and aren't sure whether to keep going or start fresh, or you want to cache hard-won research before it's lost.

  4. dev-diary v1.0.0

    moderatecheap tier only

    Keep a scannable developer journal that writes itself: discover a day's work from local Claude Code sessions, git commits, and prompt history; interview the user about what mattered and why; and record a tight, dated entry. Ships /dev-diary (write today) and /dev-diary-review (revise a past day). The journal is a separate private repo; this plugin is just the tool.

  5. diagnosing-bugs v1.0.0

    examplecheap tier only

    Diagnose a bug by writing ranked, falsifiable hypotheses before any code change, tagging temporary debug instrumentation for a zero-tolerance sweep, and gating the regression test to a red-then-green proof at the confirmed seam. Use when fixing a bug, debugging a failure, triaging an error, or the user asks to diagnose/root-cause/troubleshoot an issue.

  6. docs-hygiene v1.0.0

    subtlecheap tier only

    Audits CLAUDE.md/AGENTS.md/SKILL.md instruction files against current repo state, catches claims that have gone stale (a renamed path, a dropped command, a policy that changed) before they get trusted or acted on, and resolves contradictions between layered instruction files (root vs nested, SKILL.md vs its parent AGENTS.md) down to one explicit kept version instead of leaving both to stand. Use before trusting or propagating any instruction-file claim you haven't personally re-checked, whenever onboarding a repo's docs for the first time, right after a refactor/rename/policy change that could invalidate what's documented, or whenever two instruction files (or an instruction file and the actual repo) say different things about the same fact. Trigger phrases: 'audit the docs', 'is AGENTS.md still accurate', 'clean up CLAUDE.md', 'these instructions contradict each other', 'refactor the AGENTS.md files'.

  7. egress-gate v0.0.1

    examplecheap tier only

    Before any call that transmits repo or user content off-machine (posting a comment, pushing a branch, calling an external API with file contents in the payload), state what is being sent and to whom — permission modes gate the call, this gates the content. Use whenever output leaves the machine to a destination the user didn't name in this task.

  8. eval-ladder v0.0.1

    no example yetcheap tier only

    Design and audit an agent system's eval ladder — the cheapest rung that catches each regression, the blind spot beside every green, judges validated by TPR/TNR, pass^k for irreversible actions. Use when designing, auditing, or defending a test/eval strategy for an agent, skill, or prompt; when adding an eval tier or LLM judge; or when a suite is all-green and you cannot say what it would catch.

  9. find-before-build v0.0.1

    no example yetgraded in CI

    Search for the existing implementation before writing a new one: name the searches you ran for an existing helper, abstraction, or pattern and what they returned, before introducing anything new. Use before adding a utility, wrapper, config knob, or dependency to a codebase you did not write end-to-end.

  10. fleet-playbook-curator v1.0.0

    no example yetgraded in CI

    Deploy daily GitHub automation that curates a living, self-invalidating operating index (a 'fleet playbook') for a glob of repos — always pointing at the repos as the source of truth, never posing as it.

  11. graveyard v1.0.0

    no example yetgraded in CI

    Archive old GitHub repositories into a single private graveyard repo as restorable git bundles, then safely delete the originals. Captures full history (branches, tags, PR refs) and never deletes an original until its backup is verified.

  12. grill-me v1.0.0

    starkcheap tier only

    Interview the user about a plan before work starts, single-session and no subagents required, walking its design tree and scaling question depth to each branch's stakes (reversibility x blast radius) while offering a recommendation at almost every step. Use on phrases like grill me, interview me about this plan, stress-test this plan, or before starting a nontrivial multi-step change whose design isn't yet settled.

  13. orchestrate v1.0.0

    moderatecheap tier only

    Two reusable multi-agent orchestration templates for research-and-verify work on Claude Code's Workflow tool: fan out research over dimensions, then adversarially verify the claims that research surfaces so plausible-but-wrong findings don't survive. Ships a shared skill, two workflow-script templates (derived-verify, pipelined-verdict-wins), and a worked example.

  14. plugin-factory v1.1.0

    moderatecheap tier only

    Scaffold a new marketplace plugin skeleton in one command: a deterministic generator emits a valid plugin.json, an invariant-first SKILL.md, cross-harness AGENTS.md symlinks, a command stub, and a red-by-default eval that fails closed until you implement real checks — then wires it into the marketplace lockfile.

  15. prove-the-undo v0.0.1

    examplecheap tier only

    Rehearse the rollback before any irreversible action: name the specific restore path and demonstrate it works — never proceed on the strength of 'a backup exists'. Use before deletes, drops, force-pushes, migrations, or any action semver-gate classifies as MAJOR.

  16. recurrence-detector v0.0.1

    moderatecheap tier only

    Close the growth loop's DETECT step: read the exhaust every run already sheds — stop-reports, scope-fence findings, unmet criteria, diary entries — cluster it by failure shape, and surface any shape seen at least N times as a named candidate invariant with its sightings cited. Proposes; never scaffolds. Use when asking what keeps going wrong, or before adding a skill on a hunch.

  17. redgate v0.1.0

    moderategraded in CI

    Working harness for nontrivial work that needs explicit falsifiable criteria, verified ARM/TRACE/JUDGE rounds, or classified human gates. Compose around the most-specific specialist skill or recipe; Redgate reinforces execution and verification rather than replacing the domain procedure.

  18. scope-fence v0.0.1

    examplegraded in CI

    Keep every hunk of the diff traceable to the stated task: anything discovered outside scope is recorded as a finding (ticket, note, diary entry) — never fixed in the same change. Use when starting any bounded task, when tempted to 'fix it while I'm here', or when reviewing whether a diff crept beyond its mandate.

  19. semver-gate v1.0.0

    no example yetgraded in CI

    Classify a candidate action as PATCH/MINOR/MAJOR (semver-style blast-radius test) before acting — act silently on PATCH, flag-and-stage MINOR, stop for explicit human sign-off on MAJOR. Use whenever you're mid-task and unsure how much autonomy to take on the next action: which of several implementation paths to pick, whether to overwrite unreviewed state, whether to disable a safety toggle, or any judgment call settings.json's autoMode patterns don't enumerate.

  20. stop-rule v0.0.1

    no example yetgraded in CI

    A halting discipline for iterative fix loops: after a bounded number of failed attempts at the same objective, stop and report the state with hypotheses — never make attempt N+1 on momentum. Use when re-pushing to fix CI, retrying a flaky repro, or any loop where each retry is a guess rather than a diagnosis.

  21. tailscale-wif v1.0.0

    no example yetgraded in CI

    Set up and troubleshoot secretless GitHub Actions -> Tailscale auth via Workload Identity Federation (WIF): GitHub OIDC exchanged for short-lived Tailscale tokens, with no stored API keys or OAuth secrets.

  22. tracer-bullets v1.0.0

    moderatecheap tier only

    Ship the thinnest end-to-end slice through a system first, then widen it in place — for both software delivery and open-ended investigation/research. Use when scoping new work, de-risking unknowns, or planning how to explore an unfamiliar problem before committing to a full build.

  23. verify-before-claim v1.0.0

    no example yetgraded in CI

    Never assert a fact, completion, or reproduction claim without naming and running the specific check that would prove it false, first.

  24. voice v0.1.0

    no example yetgraded in CI

    Route every response element to exactly one voice: prose to human-voice (verdict-first, confidence-tagged), machine-read artifacts to machine-voice (compressed traces, logs, status lines); plus ai-writing-mistakes, a wording pass that strips the tells marking prose as machine-written, and second-opinion, an offer-only subagent validation pipeline that never runs unbidden.

  25. wayfinder v1.0.0

    no example yetgraded in CI

    Chart a multi-session effort as a labeled map of typed decision tickets (grilling / prototype / research / task) with explicit dependencies and an open frontier agents self-assign into. Plans; never executes.

This site is generated, and checked. The landing page, the example gallery and the timeline are each rendered from committed data by a script in docs/; the offline eval tier fails any commit whose page drifts from its data, and the Pages workflow re-checks before it deploys.