verify-before-claim
claudeCheck claims against evidence; optionally pin executable acceptance criteria and obtain independent verification for work that needs a formal contract.
4 skills · 2 commands · hooks
Plugin marketplace
Cross-harness agent plugin marketplace. Each plugin lives under plugins/<name>/ and is registered here for named installation.
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Check claims against evidence; optionally pin executable acceptance criteria and obtain independent verification for work that needs a formal contract.
4 skills · 2 commands · hooks
Route every response element to exactly one voice: prose to human-voice, machine-read artifacts to machine-voice; plus ai-writing-mistakes (wording pass) and second-opinion (offer-only validation).
4 skills · 1 command · hooks
Compile deterministic, content-hashed agents from small behavior modules: a typed AgentQuery in, an immutable AgentImage and rendered harness-native subagent out; fails closed on conflicts.
1 skill · 2 commands · 1 MCP server · hooks
Keep a scannable developer journal that writes itself: discover the day's work from sessions, commits and prompts, interview the user, record a dated entry. Ships /dev-diary and /dev-diary-review.
2 skills · 2 commands
Classify a candidate action as PATCH/MINOR/MAJOR (semver-style blast-radius test) before acting, and rehearse the rollback of any irreversible one — name the restore path and exercise it. Use mid-task when unsure how much autonomy to take.
2 skills · 2 commands
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.
1 skill · 1 command · 1 agent
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 for "design it twice".
1 skill · 1 command
Map a catalog consolidation by unit of work, not by file: one verb per entity, counts that must reconcile. Use for a "meta diff" or when merging or pruning plugins, skills, services or packages.
1 skill · 1 command
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.
1 skill · 1 command
Delegate independent work through bounded briefs, owned outputs and checked handbacks. Use when real workers help; keep small or tightly coupled work direct.
1 skill · 1 command
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 or root-causing a bug.
1 skill · 1 command
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. Use to audit docs or when instruction files contradict each other.
1 skill · 1 command
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.
1 skill · 1 command
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 or auditing a test/eval strategy.
1 skill · 1 command
Search for the existing implementation before writing a new one: name the searches run for an existing helper, abstraction, or pattern and what they returned.
1 skill · 1 command
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.
1 skill · 1 command
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 "grill me" or "stress-test this plan".
1 skill · 1 command
Scaffold a new marketplace plugin skeleton in one command: valid plugin.json, invariant-first SKILL.md, AGENTS.md symlinks, command stub, and a red-by-default eval, wired into the marketplace.
1 skill · 1 command
Close the growth loop's DETECT step: cluster the exhaust every run sheds (stop-reports, scope-fence findings, unmet criteria, diary entries) by failure shape and surface repeat shapes as named candidate invariants. Proposes; never scaffolds. Use when asking what keeps going wrong.
1 skill · 1 command
A minimal known-good plugin: the calibration baseline the counterfeit corpus mutates.
1 skill · 1 command
Keep every hunk of the diff traceable to the stated task: out-of-scope discoveries become findings (ticket, note, diary entry), never same-change fixes.
1 skill · 1 command
A halting discipline for iterative fix loops: after a bounded number of failed attempts at the same objective, stop and report state with hypotheses.
1 skill · 1 command
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 or de-risking unknowns.
1 skill · 1 command
Stress-test a contested thesis with staged, adversarial research (rival hypotheses, ACH matrix, checkpoints), plus fan-out research-and-verify Workflow templates. Not for lookups.
1 skill · 1 command
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.
1 skill · 1 command
Shows how many plugins this repo ships, and links here.