agentmods.dev

sdlc-builder

sdlc-builder is an agent for Claude Code from DarrenBenson/sdlc-studio. It costs 60 tokens per session (383 once invoked), scanned A, original, MIT.

A software-building agent for one defined unit of work, such as a story or bug, in an SDLC Studio sprint. It follows the unit's acceptance criteria and file boundaries, writes the failing test first, implements the change, and runs the specified verification.

In plain words
What is it for?
Use it to build one sprint unit from a lane brief, create its test and code, run the unit's verifier, prepare the named hand-in files, and stage only the allowed files.
Why use it?
It prevents a task from expanding beyond its agreed scope and avoids treating an unverified summary as a specification. It also keeps implementation separate from later review.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

not rated 26repo +2 today A scan 60 tokens original MIT

Good fit Use it to build one sprint unit from a lane brief, create its test and code, run the unit's verifier, prepare the named hand-in files, and stage only the allowed files.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/darrenbenson/sdlc-studio/sdlc-builder
View source ↗ DarrenBenson/sdlc-studio
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.

Clone the repo
git clone --depth 1 https://github.com/DarrenBenson/sdlc-studio

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 sdlc-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/darrenbenson/sdlc-studio/sdlc-builder/github.svg)](https://agentmods.dev/agents/darrenbenson/sdlc-studio/sdlc-builder)
Your own site
<a href="https://agentmods.dev/agents/darrenbenson/sdlc-studio/sdlc-builder"><img src="https://agentmods.dev/badge/agents/darrenbenson/sdlc-studio/sdlc-builder/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 sdlc-builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/darrenbenson/sdlc-studio/sdlc-builder"><img src="https://agentmods.dev/badge/agents/darrenbenson/sdlc-studio/sdlc-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 383 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 $0.00060 $0.00383
Opus 5.5 $0.00024 $0.00153
Sonnet 5.5 $0.00012 $0.00077
Haiku 4.5 $0.00006 $0.00038

Measured today against content hash 4d028a8139fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdlc-builder 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 today.

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/agents/sdlc-builder.md · 32 lines

What it actually says

SDLC builder

You build one unit of an SDLC Studio sprint. The lane brief your prompt names is the contract: its acceptance criteria, its Affects list and its hand-in files are law, and nothing in this definition overrides them.

How you work

  • Read the lane brief and any notes your prompt names first, each once, before anything else.
  • Refuse a unit with no authored acceptance criteria; never infer a contract from its summary.
  • Write the failing test before the code, and watch it fail for the reason the criterion names.
  • Change only the files the unit's Affects declares. A needed file outside it is a blocker to report, not a file to edit.
  • Read the part of a file you need, not the whole of a large one.
  • Run the unit's own criteria (verify_ac.py run --id <unit>) before you hand back, and carry the verifier's own output for a red one rather than a claim about it.
  • Write the hand-in files the brief names, stage exactly the Affects, and stop. Commit, push or open a pull request only when the brief says to.

Hand-back

  • Run every command in the foreground, or wait for it to finish before you hand back.
  • Hand back in at most three lines: the unit, the outcome (DONE, BLOCKED or HANDOFF), the hand-in path.
  • Send no progress message unless you are blocked.
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. today First seen · 32 lines · 60 tokens per session scan A 4d028a8139fb

Subscribe to this mod's changes

sdlc-builder is an agent published in the GitHub repository DarrenBenson/sdlc-studio (26 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 383 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Code GenerationProject managementTDDTestingbug-trackingclaude-code-skillepicsprd
Related

sdlc-builder compared with agents from other repositories

sdlc-builder next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sdlc-builderDarrenBenson/sdlc-studioAgent26todayMITA60Claude Code
test-engineerdarrenhinde/OpenAgentsControlAgent5.0k12d agoMITA19Claude Code
harness-coderJunhanliu-dev/espalier-engineeringAgent6918d agoMITA129Claude Code
harness-reviewerJunhanliu-dev/espalier-engineeringAgent6918d agoMITA114Claude Code
harness-securityJunhanliu-dev/espalier-engineeringAgent6918d agoMITA77Claude Code
tdd-workermarkshust/hcfAgent841mo agoMITA32Claude Code
implementerandyzengmath/quantum-loopAgent244mo agoMITA34Claude Code