develop

A staged feature-development command that separates research, planning, coding, and review. Specialist agents research the codebase and review the finished changes while you handle the plan and implementation.

In plain words
What is it for?
Use it to investigate an unfamiliar codebase, agree on an implementation plan, make a focused change with tests and small commits, and request targeted code, accessibility, or security reviews.
Why use it?
It gives feature work a clear order and makes important checks less likely to be skipped. It also surfaces relevant files, conventions, and review issues before handoff.

Command

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/atuljha23/holocron/develop
Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 365 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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.00365
Opus 5 $0.00014 $0.00182
Sonnet 5 $0.00005 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured yesterday against content hash ccddbe5bd7f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

develop 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 yesterday.

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.

commands/develop.md · 41 lines

What it actually says

/holocron:develop

Feature: $ARGUMENTS

Run this in four explicit phases. Do not skip ahead.

Phase 1 — Research (delegate)

Spawn @architect (or @frontend-engineer / @backend-engineer depending on the feature) via the Agent tool to:

  • Read adjacent code and summarize conventions.
  • Identify reusable primitives already in the repo.
  • List relevant constraints (data contracts, consumers, SLAs).

Cap the research report at ~300 words. Bring back file paths, not just prose.

Phase 2 — Plan (you)

With research in hand, enter plan mode (/holocron:plan-style scaffold). Present options if they exist. Get approval before writing code.

Phase 3 — Implement (you)

  • Match conventions found in Phase 1.
  • Minimum viable change. No speculative abstractions.
  • Write a test first where the contract is clear; write the code, then the test when exploratory.
  • Commit in atomic chunks — one logical change per commit.

Phase 4 — Review (delegate)

Spawn @code-reviewer on the diff. Surface blockers before handing back to the user. If the change is UI, also spawn @a11y-auditor. If server-side and non-trivial, @security-reviewer.

Exit

End with: summary of what was built, files changed, tests added, and the commands the user can run to verify.

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. yesterday First seen · 41 lines · 27 tokens per session scan A ccddbe5bd7f1

Subscribe to this mod's changes

develop is a command published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 365 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 2026-08-31.