Skip to content

AgriciDaniel/agentic-habits / skills/habits

Agentic habits. Give an agent standing behavior that survives the end of a chat, in three tiers: stated rules placed where their trigger fires, gates that make the ones that must not fail deterministic, and an evidence-bound judge that scores adherence from a fresh context. Use for /habits, and whenever someone says from now on, always do this, stop doing that, remember to, make this stick, agent habits, bad habits, how do I know you actually did it, or asks why the agent keeps repeating a mistake.

assets/templates/case.md

View on GitHub
---
type: case
title: "<short title>"
status: current
created: <YYYY-MM-DD>
updated: <YYYY-MM-DD>
tags: ["#type/case", "#habit/<ID>"]
verdict: <PASS|FAIL|N/A|UNKNOWN>
source: <observed|reported|judge>
related: ["<HABIT-ID>"]
---

# <YYYY-MM-DD> <short title>

A case is evidence. Once written it is not revised to match a later decision:
if the reading changes, write a new case and link it. Correcting a typo is fine;
rewriting what happened is not.

**What happened.** Two or three sentences. What the agent did, at what moment,
and what it cost. Written so someone who was not there can recognize the shape
when it happens again.

**Evidence.** The quote, the line reference, the command output, or the diff
hunk. If there is none, say so and mark the verdict UNKNOWN rather than writing
a verdict the evidence cannot carry.

**Habit.** The ID this bears on, or `none` if it is a candidate for a habit that
does not exist yet.

**Worked pair.** What was done, beside what the habit asks for. This is the part
that teaches, and it is why cases are worth keeping.

> Instead of: "Fixed. The build is green."
>
> The habit asks for: "Fixed. `npm run build` exits 0, output below."

**Outcome.** What changed because of this case: habit sharpened, placement
moved, gate proposed, habit retired, or nothing yet.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall