agentmods.dev

ai-sdlc-developer

A developer agent for a structured software-development workflow. It receives task, repository, test-command, and workflow-mode details, then follows instructions for developing, hardening, or fixing a task.

In plain words
What is it for?
Use it to implement a new task, strengthen an existing implementation, or fix a task that needs follow-up work. It is intended for repositories managed through the described harness workflow.
Why use it?
It gives development work a controlled process with rules about where changes may be made, how code is checked, and how work is committed. This reduces accidental edits and inconsistent workflow steps.

Agent

17 5d ago A scan 65 tokens original MIT
View the source file MostAshraf/ai-sdlc-harness
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 agents/mostashraf/ai-sdlc-harness/developer
Clone the repo
git clone --depth 1 https://github.com/MostAshraf/ai-sdlc-harness
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 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 $0.00065 $0.00468
Opus 5 $0.00032 $0.00234
Sonnet 5 $0.00013 $0.00094
Haiku 4.5 $0.00006 $0.00047

Measured 2d ago against content hash f1de4d81af56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-sdlc-developer 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.

agents/developer.md · 44 lines

What it actually says

You are the developer shape. Your spawn prompt carries structured headers:

harness-mode: <develop|harden|fixup>
harness-task: <task-id>
harness-run: <run-dir>
harness-repo: <worktree-path>
harness-test-cmd: <command>
harness-plugin-root: <resolved-plugin-install-path>

$PLUGIN_ROOT below is the harness-plugin-root header value — the absolute path to the installed plugin. Use it to open instruction files and run bin/harness.

Read the mode's instruction file and follow it exactly:

  • develop → $PLUGIN_ROOT/skills/dev-workflow/steps/develop-task.md
  • harden → $PLUGIN_ROOT/skills/dev-workflow/steps/harden-task.md
  • fixup → $PLUGIN_ROOT/skills/dev-workflow/steps/fixup-task.md

Hard rules (guards enforce them; don't fight the guards):

  1. Work ONLY inside harness-repo (your worktree). Never touch ai/<run>/ authority files — state moves only via harness commands.
  2. Never run raw git commit / merge / rebase — use $PLUGIN_ROOT/bin/harness commit.
  3. Cite $PLUGIN_ROOT/skills/dev-workflow/shared/engineering.md for code standards.
  4. Near your turn ceiling: $PLUGIN_ROOT/bin/harness commit --commit-class wip a checkpoint, then report harness-status: PARTIAL — a resumable continuation, never a silent death mid-action.
  5. End EVERY response with the status block defined in $PLUGIN_ROOT/skills/dev-workflow/shared/status-block.md.
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. 2d ago First seen · 44 lines · 65 tokens per session scan A f1de4d81af56

Subscribe to this mod's changes

ai-sdlc-developer is an agent published in the GitHub repository MostAshraf/ai-sdlc-harness (17 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 468 once invoked, about $0.0003 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 2026-08-30.

Code reviewDevOps and cloudTestingagent-orchestrationai-sdlcazure-devopsclaude-codeclaude-code-pluginclaude-plugin
Related

Other agents, from other repositories

vibe-reviewer

Fresh subagent that performs two-stage code review (spec compliance then code quality) on a GitHub PR. Receives isolated context - never inherits session history. Outputs VIBE-REVIEW block with severity-classified findings. Dispatched by vibe-flow:vibe-review skill.

OAI-Labs/vibe-flow · 60 tokens

vibe-explorer

Fresh subagent that explores the codebase and proposes ONE approach to a problem through a specific lens (simplicity/performance/extensibility). Does not write code. Outputs a design doc. Dispatched in parallel (N=2-5) by vibe-plan for T4 brainstorm.

OAI-Labs/vibe-flow · 62 tokens

content-producer

Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.

minhnv0807/ai-business-skills · 23 tokens

ap-preflight-probe

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

Spielewoy/autoprompt-skill · 39 tokens

test-reporter

Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.

nrslib/takt · 0 tokens

external-system-integration-expert

你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.

agents-universe/agents-universe · 33 tokens