develop

A guided development workflow that takes a coding task from research through planning, implementation, and checks. It remembers earlier decisions and feedback to inform later work.

In plain words
What is it for?
Use it to investigate an unclear task, define success criteria, plan file changes, implement them step by step, and compare the result with the plan.
Why use it?
It reduces misunderstandings, unplanned changes, and skipped checks by requiring clear goals, feasibility review, approval, and verification.

Command for Claude Code

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/hautc-it/cil/develop
Clone the repo
git clone --depth 1 https://github.com/hautc-it/cil

Made for: Claude Code.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 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 $0.00022 $0.00370
Opus 5 $0.00011 $0.00185
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured yesterday against content hash 20d8d1d2a58d, 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.

.claude/commands/develop.md · 33 lines

What it actually says

/develop $ARGUMENTS

1. Research

  • If $ARGUMENTS is ambiguous, present 2–3 interpretations and confirm before proceeding.
  • Read relevant files; map what already exists (Grep/Glob).
  • Run memory_search("$ARGUMENTS") AND memory_search("feedback") (replay prior corrections).
  • List assumptions explicitly. Define verifiable, concrete success criteria.

2. Feasibility — proceed only if total ≥ 35/50

Dim /10 Notes
Scope clarity well-defined?
Pattern familiarity similar code here?
Dependency awareness what does it touch?
Edge cases failure modes understood?
Test strategy how to verify?

If < 35: return to Research and resolve gaps before planning.

3. Plan — block on user approval

Goal (one sentence) · Files to modify (with reason) · Files to create (with reason) · Steps (numbered, each independently completable) · Risks · Mitigations.

4. Implement

One step at a time. Verify after each unit. Touch only what's in the plan — no opportunistic refactors. If blocked or plan changes: stop and report, don't improvise.

5. Verify

Read diff vs plan · check each success criterion · scan adjacent code for regressions · run /review if changes are significant. Store key decisions: memory_store("decision", "what + why", ["$ARGUMENTS"]).

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 · 33 lines · 22 tokens per session scan A 20d8d1d2a58d

Subscribe to this mod's changes

develop is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 370 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.