codify

codify is a command for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 25 tokens per session (5,041 once invoked), scanned A, original, Apache-2.0.

A command that loads the fifth phase of a workspace process and updates existing agents and skills with knowledge from the project. It uses the project's briefs, validation results, and documentation as its input.

In plain words
What is it for?
Updating project-specific agent and skill files after validation has completed.
Why use it?
It turns validated project knowledge into reusable instructions for future work in that workspace.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/bin/codify-backlog.mjs.

Good fit Updating project-specific agent and skill files after validation has completed.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-py
agentmods
npx agentmods add commands/terrene-foundation/kailash-coc-claude-py/codify

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codify

README.md
[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/codify/github.svg)](https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/codify)
Your own site
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/codify"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/codify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codify

Your own site · 80×15
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/codify"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/codify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.05041
Opus 5 $0.00013 $0.02521
Sonnet 5 $0.00005 $0.01008
Haiku 4.5 $0.00003 $0.00504

Measured 6d ago against content hash c9e1ccd02d5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

codify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/codify.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Resolution

  1. If $ARGUMENTS specifies a project name, use workspaces/$ARGUMENTS/
  2. Otherwise, use the most recently modified directory under workspaces/ (excluding instructions/)
  3. If no workspace exists, ask the user to create one first
  4. Read all files in workspaces/<project>/briefs/ for user context (this is the user's input surface)

Phase Check

  • Read workspaces/<project>/04-validate/ to confirm validation passed
  • Read docs/ and docs/00-authority/ for knowledge base
  • Output: update existing agents and skills in their canonical locations. Which locations exist depends on the repo's tier subscriptions — Kailash-subscribing targets carry the framework trees (agents/frameworks/, skills/01-core-sdk/, skills/02-dataflow/, …); a stack-agnostic base template carries none of them, so codify into the agent/skill trees that repo actually has.

Execution Model

This phase executes under the autonomous execution model (see rules/autonomous-execution.md). Knowledge extraction and codification are autonomous — agents extract, structure, and validate knowledge without human intervention. The human reviews the codified output at the end (structural gate on what becomes institutional knowledge), but the extraction and synthesis process is fully autonomous.

Workflow

0. Acquire codify lease (multi-operator concurrency gate)

Per (loom-internal reference) §7.1: two concurrent /codify invocations clobber the rule corpus. Acquire the lease BEFORE any step below.

Call acquireCodifyLease({ scopeFiles, displayId }) from .claude/hooks/lib/codify-lease.js. The helper unions .claude/learning/learning-codified.json + .claude/.proposals/latest.yaml into the scope automatically. displayId comes from operator-id.js::resolveIdentity().

On { ok: false, reason: "conflict" }: STOP, surface the conflicting display_id + acquired_at + scope overlap to the user verbatim, plus liveness.basis (why the lease is still judged HELD). Silent proceed is BLOCKED (rules/zero-tolerance.md Rule 3). Conversely, an { ok: true } carrying reclaimed means this acquire TOOK OVER a lease a crashed/abandoned session never released (age past the 12h LEASE_TTL_MS floor) — surface reclaimed.display_id + reclaimed.acquired_at + reclaimed.liveness.basis verbatim, and reclaimed.record_emit when it is not ok. reclaimed is absent on every normal acquire; a takeover the operator never sees is indistinguishable from the clobber the lease exists to prevent.

Read the full file on GitHub · 152 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 152 lines · 25 tokens per session scan A c9e1ccd02d5f

Subscribe to this mod's changes

codify is a command published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 21d ago), licensed Apache-2.0. It adds 25 tokens to every session and 5,041 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.