Commands · infinri/writ

writ

Hybrid RAG rule retrieval + session-aware workflow enforcement. Injects relevant coding rules via a 5-stage pipeline (BM25 + vector + graph traversal + reciprocal-rank fusion) and enforces mode-based workflow gates (plan -> tests -> implementation).

CLEARED_STATICclaude-onlyv1.7.0

Pipeline results

Coverage

CLEARED_STATIC

Tests run

7 / 8

Portability

Claude-only

Type

Commands

Tests & results

What the pipeline checked

TestStateResult or reason

eligibilityranall eligibility checks passed

dedupranunique -- no near-duplicate found

clocranno code measured

secretsran0 PLAUSIBLY-LIVE / 1 FLAG-INFO

egressran20 lexical match(es) — FLAG-INFO (C-01: semantic analysis deferred to v2)

injectionranno patterns matched (confidence: STANDARD)

required-fieldsranrequired fields present: name, version, description

behaviouraldeferredbehavioural assessment deferred (v1): Python with non-stdlib imports (committed-only policy): [('tests/test_phase5_instrumentation.py', 'writ'), ('tests/test_phase5_instrumentation.py', 'fastapi')]

What's inside

Components found

agents/writ-explorer.md

componentmedium

agents/writ-implementer.md

componentmedium

agents/writ-planner.md

componentmedium

agents/writ-reviewer.md

componentmedium

agents/writ-test-writer.md

componentmedium

.claude/commands/writ-approve.md

componentmedium

templates/commands/writ-approve.md

componentmedium

Coverage

Not assessed

behavioural execution not run
egress patterns logged (FLAG-INFO): 20 lexical match(es)
secret pattern(s) classified FLAG-INFO: 1 match(es)

README

From the repository

# Writ

A Claude Code harness that enforces engineering discipline at the moment the AI acts, and delivers the rules that fit the work in front of it.

## In plain terms

Give a coding AI a long list of rules and two things go wrong. It forgets them as the conversation grows, and it has no obligation to follow them anyway. You can ask an AI to write tests before code. Nothing makes it do so.

Writ changes where the rules live. Instead of putting them in the conversation and hoping, Writ sits between the AI and your files. When the AI tries to write code before you have approved a plan, the write is refused. Not discouraged, refused. And instead of showing the AI all 287 rules every time it does anything, Writ looks at what the AI is actually doing right now and hands it only the rules that apply.

The refusal part is the point. The retrieval part is what makes the refusal affordable when your rulebook grows past a handful of rules.

## The claim, and its limits

**The claim.** Instructions in a prompt decay. They get compacted away, outweighed by more recent text, or quietly reinterpreted. A check that runs at the moment the AI calls a tool does not decay. Writ moves workflow disci…

← Back to Commands