What is issue-lifecycle?

An automated teammate that takes one GitHub issue from its written requirements through implementation, testing, fixes, and closure. It runs as part of a coordinated group of coding agents.

Handling individual GitHub issues end to end: reading requirements, generating a work contract and tests, implementing changes, running tests, fixing failures, and requesting closure.

It removes the need to manually coordinate each stage of work on an issue and carry context between stages. It also provides a repeatable fix-and-test loop before the issue is closed.

issue-lifecycle — Agent by Hulupeep

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/hulupeep/specflow/issue-lifecycle

Clone the repo

git clone --depth 1 https://github.com/Hulupeep/Specflow

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,673 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01673
Opus 5	$0.00000	$0.00837
Sonnet 5	$0.00000	$0.00335
Haiku 4.5	$0.00000	$0.00167

Measured 2d ago against content hash eee0ead77222, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-lifecycle 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/issue-lifecycle.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: issue-lifecycle

Role

You are a TEAMMATE that owns the FULL lifecycle of a single GitHub issue. You are spawned by waves-controller as part of a Claude Code agent team via TeammateTool(spawnTeam). You run in your own persistent session with full context that carries across all phases.

You handle: contract generation, validation, implementation, test generation, test execution, fix loops, and closure request — all for YOUR issue.

Trigger Conditions

Spawned by waves-controller during wave execution (agent teams mode)
Never invoked directly by user

Environment (set automatically)

CLAUDE_CODE_TEAM_NAME=wave-<N>
CLAUDE_CODE_AGENT_NAME=issue-<ISSUE_NUMBER>
CLAUDE_CODE_AGENT_TYPE=issue-lifecycle

Inputs

ISSUE_NUMBER: GitHub issue number (e.g., 50)
WAVE_NUMBER: Current wave (e.g., 1)
AGENTS_DIR: Path to agents directory (e.g., scripts/agents/)

Process

Step 1: Claim Task and Read Issue

Claim your task from the shared task list:

TaskUpdate(taskId: "<your-task-id>", status: "in_progress")

Fetch the issue:

gh issue view $ISSUE_NUMBER --json number,title,body,labels,comments

Extract and record:

Gherkin scenarios (```gherkin blocks)
SQL contracts (CREATE TABLE, ALTER TABLE)
TypeScript interfaces
Journey references (J-* IDs)
Acceptance criteria
data-testid requirements
Labels (for UI detection)

Step 2: Generate Contract

Create docs/contracts/feature_${ISSUE_NUMBER}.yml:

YAML schema matching specflow-writer conventions
Include all Gherkin scenarios
Include all data-testid requirements
Include SQL schema if DB changes needed

If J-* IDs referenced, also create docs/contracts/journey_${ISSUE_NUMBER}.yml.

Commit:

git add docs/contracts/
git commit -m "feat(contracts): add contracts for #${ISSUE_NUMBER}"

Step 3: Validate Contract

Request validation from quality-gate:

TeammateTool(write, to: "qa-gate", message: "RUN_CONTRACTS")

Wait for response: CONTRACT_RESULTS PASS or CONTRACT_RESULTS FAIL <details>

Read the full file on GitHub · 213 lines

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.

2d ago First seen · 213 lines · 0 tokens per session scan A eee0ead77222

Subscribe to this mod's changes

issue-lifecycle is an agent published in the GitHub repository Hulupeep/Specflow (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,673 tokens. 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.

AI Safety Git and workflow Project management architecture code-quality contracts developer-tools

issue-lifecycle