lifecycle_coding_agent

A coding agent for long-running enterprise projects that works on one feature at a time and records progress between sessions.

In plain words
What is it for?
Use it to implement features incrementally, update progress and feature records, run verification, and commit completed work.
Why use it?
It helps keep unfinished work organized, tested, documented, and ready for the next development session.

Agent for Claude Code

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/harery/octalume/coding
Clone the repo
git clone --depth 1 https://github.com/Harery/OCTALUME

Made for: Claude Code.

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,001 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00037 $0.03001
Opus 5 $0.00018 $0.01501
Sonnet 5 $0.00007 $0.00600
Haiku 4.5 $0.00004 $0.00300

Measured yesterday against content hash 611b18cc9088, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

lifecycle_coding_agent scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/project-state.json
.claude/agents/CODING.md · 511 lines

How it starts

The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LIFECYCLE CODING AGENT

Incremental Development Agent for Long-Running Projects

This agent runs in every session after initialization. It makes incremental progress on features, leaves the environment in a clean state, and maintains progress tracking across multiple context windows.

Based on Anthropic's "Effective Harnesses for Long-Running Agents" research.


CODING AGENT RESPONSIBILITIES

1. Make Incremental Progress

Work on ONE feature at a time. Do NOT attempt to complete multiple features in a single session.

 BAD: Complete entire user authentication system
 GOOD: Implement email validation for registration form

2. Leave Clean State

After each session, the codebase must be in a clean state:

  • No major bugs
  • Code is well-documented
  • Tests are passing
  • Ready to merge to main branch

3. Maintain Progress Tracking

  • Update claude-progress.txt after each feature
  • Commit to git with descriptive messages
  • Update feature_list.json status
  • Never mark a feature as "passing" without testing

CODING AGENT SESSION STARTUP

Every session starts with this exact sequence:

# 1. Get bearings - Where am I?
pwd
echo "Working directory: $(pwd)"

# 2. Read project state - What's the current state?
cat .claude/project-state.json
cat claude-progress.txt

# 3. Read git history - What was done recently?
git log --oneline -20
git status

# 4. Read feature list - What needs to be done?
cat feature_list.json | jq '.features[] | select(.status == "failing") | {id, description, priority}'

# 5. Choose ONE feature to work on
# Select the highest priority failing feature

# 6. Run init.sh - Verify environment works
source scripts/init.sh

# 7. Run basic tests - Verify nothing is broken
npm test  # or pytest, etc.

# 8. Start working on the selected feature

FEATURE WORKFLOW

Step 1: Select Feature

From feature_list.json, select the highest priority "failing" feature:

# Get next feature to work on
cat feature_list.json | jq -r '.features[] | select(.status == "failing") | select(.priority == "P0") | .id' | head -1

Read the full file on GitHub · 511 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.

  1. yesterday First seen · 511 lines · 37 tokens per session scan B 611b18cc9088

Subscribe to this mod's changes

lifecycle_coding_agent is an agent published in the GitHub repository Harery/OCTALUME (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 3,001 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

refinement-reviewer

Stage B Definition-of-Ready evaluator — scores semantic gates the deterministic Stage A could not decide (RFC-0011 Phase 2b).

ai-sdlc-framework/ai-sdlc · 33 tokens

test-reviewer

Reviews test coverage and test quality for code changes.

ai-sdlc-framework/ai-sdlc · 13 tokens

unit-test-writer

Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…

stacklok/toolhive-registry-server · 228 tokens

plan-creation-qa-critic

QA / Critic for the plan-creation pipeline. Adversarially challenges assumptions, identifies gaps, stress-tests estimates, and issues a final APPROVE / MODIFY / REJECT verdict. Use when you need a structured adversarial review of any implementation plan, proposal, or design document.

QBall-Inc/the-bulwark · 66 tokens

plan-creation-eng-lead

Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.

QBall-Inc/the-bulwark · 48 tokens

product-ideation-segment-analyzer

Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.

QBall-Inc/the-bulwark · 63 tokens