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.
npx agentmods add commands/harery/octalume/lifecycle-featuregit clone --depth 1 https://github.com/Harery/OCTALUMEWrote 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.
[](https://agentmods.dev/commands/harery/octalume/lifecycle-feature)<a href="https://agentmods.dev/commands/harery/octalume/lifecycle-feature"><img src="https://agentmods.dev/badge/commands/harery/octalume/lifecycle-feature.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00009 | $0.00749 |
| Opus 5 | $0.00005 | $0.00375 |
| Sonnet 5 | $0.00002 | $0.00150 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade B, and why
lifecycle_feature 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 4d 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.
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 How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work on Feature
Work on feature $ARGUMENTS following the incremental development approach.
Feature Workflow
-
Get Oriented: Start each session by getting oriented:
pwd cat .claude/project-state.json cat claude-progress.txt git log --oneline -20 git status -
Select Feature: Choose ONE feature to work on:
cat feature_list.json | jq '.features[] | select(.status == "failing")'- Select the highest priority failing feature (P0 > P1 > P2 > P3)
- Do NOT work on multiple features in one session
-
Read Feature Details: Get complete feature information:
cat feature_list.json | jq ".features[] | select(.id == \"F-XXX\")" -
Plan Implementation: Create an implementation plan:
- Current state
- Changes required
- Files to modify
- Acceptance criteria
- Verification steps
-
Implement Feature: Write the code:
- Follow coding standards
- Write clear comments
- Handle errors properly
- Consider security implications
-
Write Tests: Write comprehensive tests:
- Unit tests for individual functions
- Integration tests for component interactions
- E2E tests for user workflows
-
Test Manually: Test as a human user would:
- Start development server:
source scripts/init.sh - Navigate to the feature
- Test all acceptance criteria
- Verify all verification steps
- Start development server:
-
Update Feature Status: Only after thorough testing:
jq '.features[] |= if .id == "F-XXX" then .status = "passing" else . end' feature_list.json > feature_list.json.tmp mv feature_list.json.tmp feature_list.json -
Commit Progress: Commit to git with descriptive message:
git add . git commit -m "feat: [feature description] (F-XXX) - [what was done] - [tests added] - [verification steps completed] Artifacts: P5-CODE-XXX, P5-TEST-XXX Feature: F-XXX Status: passing " -
Update Progress: Update claude-progress.txt:
cat >> claude-progress.txt <<EOF ### Session N - F-XXX Complete **Feature**: [feature description] **Status**: PASSING **Tests**: Unit + Integration + E2E **Artifacts**: P5-CODE-XXX, P5-TEST-XXX EOF
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.
- 4d ago First seen · 113 lines · 9 tokens per session scan B fd31c67e42b5
lifecycle_feature is a command published in the GitHub repository Harery/OCTALUME (2 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 749 once invoked, about $0.0000 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.
Other commands, from other repositories
dispatch-worker
Run one in-session-agent Worker tick (RFC-0041 §4.3.1).
version
Show installed vs latest ai-sdlc plugin version. Bypasses the 24h SessionStart cache.
spec-intake
Execute the canonical workflow: .agent/workflows/spec-intake.md.
test
Execute the canonical workflow: .agent/workflows/test.md.
au-aescsf
You are an enterprise architect generating an Australian Energy Sector Cyber Security Framework (AESCSF) maturity assessment for an Australian energy-sector project, asset, market interface, OT environment, DER platform, or regulated energy business capability.
au-pspf
You are an enterprise architect generating a Protective Security Policy Framework (PSPF) compliance assessment for an Australian Government entity or contractor handling government information.