UnpaidAttention

UnpaidAttention/fable5-methodology

Plugin Claude Code

Plugin marketplace listing 1 plugin: fable5-methodology.

UnpaidAttention/fable5-methodology

Plugin Claude Code

Self-enforcing engineering methodology extracted from Claude Fable 5 for less advanced models: prime directives + integrity rules injected each session, 26 on-demand skills, 4 contracted subagents (builder, qa-verifier, code-reviewer, research-scout), and 6 lifecycle hooks that gate destructive commands and unverified.

UnpaidAttention/fable5-methodology

Instructions file

Claude Code instructions for UnpaidAttention/fable5-methodology, covering operating manual (master), a. prime directives (inline — always active), e. standing instructions and g. non-transferable limits — compensate mechanically.

UnpaidAttention/fable5-methodology

Agent

Implements a single scoped change that already has explicit acceptance criteria. Delegate to builder when a task is specified enough to hand off — a defined change with a list of what "done" looks like and the files/area in scope. Do NOT use for open-ended exploration, design decisions, or anything lacking acceptance…

UnpaidAttention/fable5-methodology

Agent

Adversarially reviews a diff cold — without the reasoning that produced it — for correctness, safety, design, and scope, hunting specifically for fake progress, silently dropped requirements, weakened tests, and scope creep. Delegate to code-reviewer for any non-trivial diff before it is accepted or committed…

UnpaidAttention/fable5-methodology

Agent

Independently verifies a completed change against its acceptance criteria by running the tests/build/lint itself and probing edge cases — never trusting the implementer's claims. Delegate to qa-verifier after any builder (or your own) implementation, before accepting it as done. Requires the change and its acceptance…

UnpaidAttention/fable5-methodology

Agent

Answers questions about an API, library version, CLI flag, config option, or current best practice by checking the installed environment first and then version-matched official docs — never from training memory alone. Delegate to research-scout before relying on any version-sensitive external fact, or when the user…

UnpaidAttention/fable5-methodology

Hook

Runs before the agent uses a tool for Bash tool calls, executing pre-tool-guard.py via python3. From UnpaidAttention/fable5-methodology.

UnpaidAttention/fable5-methodology

Hook

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing post-edit-verify.sh and evidence-log.sh via bash (2 commands). From UnpaidAttention/fable5-methodology.

UnpaidAttention/fable5-methodology

Hook

Runs when the agent finishes a response, executing delivery-gate.sh via bash. From UnpaidAttention/fable5-methodology.

UnpaidAttention/fable5-methodology

Hook

Runs before the context is compacted, executing pre-compact-handoff.sh via bash. From UnpaidAttention/fable5-methodology.

UnpaidAttention/fable5-methodology

Hook

Runs when a session starts, executing inject-directives.sh and session-loader.sh via bash (2 commands). From UnpaidAttention/fable5-methodology.

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Choose between competing technical approaches and make design decisions with an explicit trade-off order. Trigger this when a task requires selecting among 2+ viable designs — "should we use X or Y", designing a schema, shaping a public API, choosing a storage/queue/cache mechanism, deciding whether to add a…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Review a diff or pull request — including your own before delivery — in a fixed pass order (correctness, then safety/security, then design, then style) and report findings ranked by severity. Trigger this when asked to review a PR or diff, when checking over a change before committing or handing it off, and as the…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Map an unfamiliar repository before changing anything in it — structure sweep, entry points, configs, test baseline, targeted tracing, and mental-model confirmation. Trigger this the FIRST time you work in a repo (or an unfamiliar subsystem of a known repo) in a session, before your first edit there — whenever the…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Protect the context window as a scarce resource — read at the right altitude, delegate bulk reconnaissance to subagents so only conclusions enter the main thread, externalize durable facts to disk, and respond to your own degradation signals. Trigger this when about to read a large file or many files, when a…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Recognize mid-task that the current APPROACH is wrong and execute a disciplined stop-revert-replan instead of accumulating patches. Trigger this when any alarm fires during ongoing work: your last two changes each fixed the previous change's symptom; the design keeps growing special cases; you're fighting or…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Step-by-step procedure for diagnosing and fixing failures — reproduce, read, hypothesize, bisect, fix, regression-test. Trigger this whenever something does not work as expected — a bug report, a failing or flaky test, a crash, an error message, wrong output, "it worked yesterday", or unexpected behavior during your…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Add, upgrade, or migrate third-party dependencies safely — read the changelog for the exact version jump, isolate the change, run full verification, and keep rollback ready. Trigger this when the task involves bumping a package version, adding a new dependency, replacing one library with another, resolving a…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Externalize reasoning to a scratchpad file for problems too large to hold in working memory — a persistent record of candidate approaches, eliminated branches and WHY they were eliminated, open questions, and current best hypothesis, updated as understanding evolves. Trigger this when a problem has more moving parts…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Rules for commits, branches, diffs, and history when working in a git repository — checkpoint strategy, pre-commit diff review, message format, and the hard prohibitions on destructive operations. Trigger this whenever work happens in a git repo and involves staging, committing, branching, or any history-affecting…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Concrete coding conventions to apply WHILE writing or editing code — naming, function/file size, error handling, input validation, types, comments, tests, and secrets. Trigger this whenever you are about to write new code or modify existing code in any language, including tests and scripts. Do NOT trigger for choosing…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Build large multi-part deliverables — multi-file projects, migrations, long documents, N-of-the-same-thing work — in verified increments with dependency ordering, checkpoints, a running state note, and consistency sweeps. Trigger this when a task will produce 3+ files, spans more sub-deliverables than fit in one pass…

UnpaidAttention/fable5-methodology

Skill Claude CodeCodex

Compact honesty and safety guardrails that apply to ANY task involving file modification, command execution, or reporting results — the absolutes on claiming success, fabricating output, silencing tests, dropping requirements, destructive commands, scope, and secrets. Trigger this on effectively every working task…