loop-sdd-cycle

loop-sdd-cycle is a skill for Claude Code, Codex from jsuvic/agent-profile. It costs 35 tokens per session (373 once invoked), scanned A, original, Apache-2.0.

A bounded development routine that moves one approved change through specification, tests, implementation, and final review. TDD means writing a failing test first, then changing the code until the test passes.

In plain words
What is it for?
For completing a focused change through spec-first work, a failing test, the smallest implementation, and verification against acceptance criteria, with approval required before changes are written.
Why use it?
It keeps requirements and tests aligned and stops after a small number of attempts or when progress stops, rather than looping indefinitely.

Skill for Claude CodeCodex

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 skills/jsuvic/agent-profile/loop-sdd-cycle
Any agent
npx skills add jsuvic/agent-profile --skill loop-sdd-cycle
Clone the repo
git clone --depth 1 https://github.com/jsuvic/agent-profile

Made for: Claude Code, Codex.

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 loop-sdd-cycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/jsuvic/agent-profile/loop-sdd-cycle.svg)](https://agentmods.dev/skills/jsuvic/agent-profile/loop-sdd-cycle)
Your own site
<a href="https://agentmods.dev/skills/jsuvic/agent-profile/loop-sdd-cycle"><img src="https://agentmods.dev/badge/skills/jsuvic/agent-profile/loop-sdd-cycle.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 373 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 $0.00035 $0.00373
Opus 5 $0.00017 $0.00187
Sonnet 5 $0.00007 $0.00075
Haiku 4.5 $0.00003 $0.00037

Measured 3d ago against content hash 7a4f9ed2e7f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-sdd-cycle 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 3d 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.

fixtures/automation-pack-enabled/expected/.agents/skills/loop-sdd-cycle/SKILL.md · 42 lines

What it actually says

Loop: SDD Cycle

Advance one approved spec slice through spec, tests, implementation, and verification in bounded iterations. Each iteration takes the smallest slice that keeps the spec and its tests in step.

Loop Steps

  1. Confirm the slice against the approved spec; run sdd-change for the spec-first discipline.
  2. Add or update a focused failing test for the slice; run tdd-change for the red/green discipline.
  3. Implement the smallest change that satisfies the failing test and the spec.
  4. Verify the slice against the spec and acceptance criteria; run final-review before handoff.

Max Iterations

The loop runs at most 3 iterations. When it reaches 3 iterations without meeting a stop condition, it stops unconditionally and reports the unfinished state and the outstanding work; it never raises the bound to keep going.

Stop Conditions

Stop the loop as soon as any of these holds:

  • The relevant tests and checks are green.
  • An iteration produces no diff.
  • The same failure repeats identically across two consecutive iterations.

Approval Gate

  • Get explicit human approval before any write, commit, or destructive step in each iteration.
  • The loop never self-approves, never continues past the iteration bound, and never runs destructive commands on its own authority.
  • Pause and surface the state whenever approval is missing.

Safety

  • Do not upload source code.
  • Do not read or print secrets.
  • APC does not run this loop; a human or agent follows these instructions and remains in control.
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. 3d ago First seen · 42 lines · 35 tokens per session scan A 7a4f9ed2e7f7

Subscribe to this mod's changes

loop-sdd-cycle is a skill published in the GitHub repository jsuvic/agent-profile (3 stars, last pushed 10d ago), licensed Apache-2.0. It adds 35 tokens to every session and 373 once invoked, about $0.0002 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.