What is recursive-init?

A command that starts a tracked recursive work run for a feature or bug fix. It creates the run folder and initial requirements and worktree documents.

Use it to initialize a run with a chosen ID, feature or bug-fix template, and optionally an issue reference.

It gives a multi-step coding effort a consistent starting point and records the Git state needed to verify the work.

recursive-init — Command by try-works

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/try-works/recursive-mode/recursive-init

Clone the repo

git clone --depth 1 https://github.com/try-works/recursive-mode

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 583 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00583
Opus 5	$0.00000	$0.00292
Sonnet 5	$0.00000	$0.00117
Haiku 4.5	$0.00000	$0.00058

Measured 2d ago against content hash f609e3a9978a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recursive-init 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 2d 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.

docs/templates/commands/recursive-init.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

recursive-init (prompt template)

Paste this into chat if your agent does not support custom slash commands.

Usage Pattern

Initialize recursive run: <run-id> [options]

Script (Recommended)

python "<SKILL_DIR>/scripts/recursive-init.py" --repo-root . --run-id "<run-id>" --template feature
python "<SKILL_DIR>/scripts/recursive-init.py" --repo-root . --run-id "<run-id>" --template bugfix --from-issue "#123"
python3 "<SKILL_DIR>/scripts/recursive-init.py" --repo-root . --run-id "<run-id>" --template feature

powershell -ExecutionPolicy Bypass -File "<SKILL_DIR>/scripts/recursive-init.ps1" -RepoRoot . -RunId "<run-id>" -Template feature
pwsh -NoProfile -File "<SKILL_DIR>/scripts/recursive-init.ps1" -RepoRoot . -RunId "<run-id>" -Template feature

What It Does

Creates /.recursive/run/<run-id>/
Generates 00-requirements.md
Generates a prefilled 00-worktree.md scaffold with executable Phase 0 diff-basis fields when git state can be resolved
Validates that the recorded Phase 0 diff basis is executable against live git state before returning success
Creates addenda/, subagents/, router-prompts/, and evidence/ subfolders
Creates canonical evidence subfolders including review-bundles/ and router/
Marks the run as recursive-mode-audit-v2
If recursive-training is installed, calls /.recursive/scripts/recursive-training-loader.py so the new run starts with memory-index-driven experiential context

Output

/.recursive/run/<run-id>/00-requirements.md
/.recursive/run/<run-id>/00-worktree.md
/.recursive/run/<run-id>/addenda/
/.recursive/run/<run-id>/subagents/
/.recursive/run/<run-id>/router-prompts/
/.recursive/run/<run-id>/evidence/{screenshots,logs,perf,traces,review-bundles,router,other}/

Diff Basis Notes

The generated 00-worktree.md uses the current HEAD commit as the safe default baseline when possible.
Normalized baseline, Normalized comparison, and Normalized diff command are treated as executable source-of-truth fields.
If you later change the baseline reference during Phase 0, update every diff-basis field and rerun lint before locking.

Read the full file on GitHub · 53 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.

2d ago First seen · 53 lines · 0 tokens per session scan A f609e3a9978a

Subscribe to this mod's changes

recursive-init is a command published in the GitHub repository try-works/recursive-mode (129 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 583 tokens. 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 2026-08-30.

Data and AI Debugging Git and workflow

recursive-init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

recursive-init (prompt template)

Usage Pattern

Script (Recommended)

What It Does

Output

Diff Basis Notes

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement