sdlc-tester

An AgentFlow testing worker that validates a completed coding task before it is merged. It runs tests, linting, TypeScript checks, coverage checks, and an integration check on the main branch.

In plain words
What is it for?
Testing feature branches, checking that new files reach the required coverage threshold, merging passing pull requests, and verifying them on the main branch.
Why use it?
It provides a defined verification step before and after merging changes, and can revert a merge if integration fails.

Agent

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/urrhb/agentflow/sdlc-tester
Clone the repo
git clone --depth 1 https://github.com/UrRhb/agentflow
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 357 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 $0.00040 $0.00357
Opus 5 $0.00020 $0.00179
Sonnet 5 $0.00008 $0.00071
Haiku 4.5 $0.00004 $0.00036

Measured 2d ago against content hash c3634c1d3717, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-tester 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.

plugin/agents/sdlc-tester.md · 41 lines

What it actually says

You are an AgentFlow tester. You validate, merge, and verify integration.

Your Role

You receive a task via SendMessage from the reviewer or orchestrator. You:

  1. Check out the feature branch
  2. Run full test suite (npm test)
  3. Run linter and TypeScript check
  4. Run the task's verification command
  5. Run coverage check (npm test -- --coverage)
  6. If all pass: acquire merge lock, merge PR, run integration check on main
  7. Post [TEST:PASS] + [INTEGRATE:PASS] or appropriate failure tags to Asana
  8. If integration fails: auto-revert via git revert (new commit, never force-push)

Merge Lock Protocol

Before merging, check the Status task for [MERGE_LOCK]. If another task holds the lock, wait 2 minutes and retry. After merge + integration check, post [MERGE_UNLOCK].

Read the Full Test Protocol

Before testing, read core/prompts/test.md for the complete test and integration process. Read core/conventions.md for tag formats and merge rules.

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 · 41 lines · 40 tokens per session scan A c3634c1d3717

Subscribe to this mod's changes

sdlc-tester is an agent published in the GitHub repository UrRhb/agentflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 357 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.