Turn an active goal contract into an ordered plan where every step carries its own check, then verify the plan against the goal before any code is written: each criterion is covered by at least one step, no step touches a non-goal, and the first step is the one that retires the most uncertainty.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Plan
## Purpose
A plan written from memory of the request drifts from the contract. This skill writes the
plan from the goal file and checks it against the same file, so the work that follows is
judged by criteria that existed before the plan did. The host's native plan mode, when one
exists, is a fine place to draft; the goal file is where the plan is kept.
## Procedure
1. **Read the goal file.** Refuse to plan a goal whose status is not `active`, or whose
criteria table is empty. Enforce its token budget before further work; unavailable
accounting for a finite token limit blocks. Refuse a new plan when `iterations_used`
has reached the finite iteration limit: set `exhausted`, retain evidence and stop.
2. **Read the code the criteria touch.** Open every existing file a criterion reads or a
step will change. For a new file, record its absence and inspect its parent directory
and neighboring conventions before planning its creation.
3. **Draft the steps.** Each step states: what changes, in which files, which criteria it
serves, and the check that proves the step is done (a command, or a reviewer reading a
…
The line at the top of this page pins the label git:20260917.db5f697, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_3mh2faqdmjg23hfg
GET https://markdownregistry.com/api/v1/resolve?ref=cdeust/zetetic-team-subagents/plan
GET https://markdownregistry.com/api/v1/blob/32915d44d26b2c3028b24864403cd1da8d89664fa8cd98ca7b1246a3baefe208
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
cdeust/zetetic-team-subagents · plugins/zetetic-design/skills/design/SKILL.md · UX/UI design and accessibility audit -- name the user, task, and success criterion before any layout decision, enforce…
cdeust/zetetic-team-subagents · plugins/zetetic-loop/skills/advisor-model/SKILL.md · Consult a separate model at a selected plan, fork, or completion decision while the current model retains execution…
cdeust/zetetic-team-subagents · plugins/zetetic-loop/skills/goal/SKILL.md · Compile a long-running objective into a persistent, host-neutral goal contract: one measurable end state, non-goals…
cdeust/zetetic-team-subagents · plugins/zetetic-loop/skills/refine-goal/SKILL.md · After a verify-goal run, turn the ledger into the next iteration: tighten criteria that passed by accident, add the…
cdeust/zetetic-team-subagents · plugins/zetetic-loop/skills/verify-goal/SKILL.md · Run every acceptance criterion of a goal file as an external check, record the command, its exit code and an output…
cdeust/zetetic-team-subagents · plugins/zetetic-reasoning/skills/evidence-synthesis/SKILL.md · Synthesize multiple papers, benchmarks, interviews, reviews, or other sources into a defensible and qualified…
cdeust/zetetic-team-subagents · skills/boundary-design/SKILL.md · Draw the line where it costs least. Use for build-vs-buy calls, "where does this module/team/service boundary belong?"…
cdeust/zetetic-team-subagents · skills/causal-audit/SKILL.md · Correlation walked in; make it prove causation. Use when someone claims "X causes Y" from observational data, asks "did…
cdeust/zetetic-team-subagents · skills/decision-bias-check/SKILL.md · Audit the decision before it ships. Use for "are we sure about this?", high-stakes choices made on fast intuition…
cdeust/zetetic-team-subagents · skills/estimation/SKILL.md · Bound it before you build it. Use when a decision is blocked by "we don't have data", an estimate looks suspiciously…
jeremylongshore/tons-of-skills-marketplace · plugins/ai-agency/hyperflow/skills/plan/SKILL.md · Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to…
zereight/gitlab-mcp · .github/skills/plan/SKILL.md · Strategic planning with optional interview workflow. Activate when user says: plan this, plan the, let's plan, make a…
suboss87/fdeops · skills/plan/SKILL.md · Sequence an understood outcome into verifiable delivery slices with dependencies, ownership and acceptance checks. Use…
snowflake-labs/cocoplus · .cortex/skills/cocobrew/plan/SKILL.md · Enter the Plan phase of CocoBrew. Runs CocoSpec quality gate pre-flight, reads spec.md and discuss.md (if present)…
boshu2/agentops · skills/plan/SKILL.md · Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions. Use…
boshu2/agentops · plugin/skills/plan/SKILL.md · Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions. Use…
