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-phasegit 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-phase)<a href="https://agentmods.dev/commands/harery/octalume/lifecycle-phase"><img src="https://agentmods.dev/badge/commands/harery/octalume/lifecycle-phase.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 | $0.00011 | $0.00570 |
| Opus 5 | $0.00005 | $0.00285 |
| Sonnet 5 | $0.00002 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
lifecycle_phase 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Lifecycle Phase
Execute Phase $ARGUMENTS of the Unified Enterprise Lifecycle.
Phase Execution Steps
-
Load Phase Skill: Read the phase-specific SKILL.md file:
skills/phase_{PHASE_NUMBER}_{PHASE_NAME}/SKILL.md -
Validate Entry Criteria: Check that all entry criteria are met:
- Previous phase deliverables complete
- Required approvals obtained
- Artifacts created and archived
-
Read Project State: Load current project state:
.claude/project-state.jsonclaude-progress.txtfeature_list.json
-
Execute Phase Activities: Follow the phase workflow:
- Read phase steps from SKILL.md
- Execute each step with appropriate owner and participants
- Create required artifacts
- Get required approvals
-
Validate Exit Criteria: Ensure all exit criteria are met:
- All deliverables complete
- All artifacts created
- All approvals obtained
- Quality gates passed
-
Go/No-Go Decision: Execute go/no-go decision:
- Prepare recommendation
- Get secondary owner review
- Get executive sponsor approval
- Document decision
-
Update Project State: Update all tracking files:
- Update
.claude/project-state.json - Update
claude-progress.txt - Update
feature_list.json - Archive artifacts to appropriate phase directory
- Update
-
Commit Progress: Commit all work to git:
git add . git commit -m "feat: complete Phase {N} - {PHASE_NAME} - [Summary of deliverables] - [Artifacts created] - [Approvals obtained] Artifacts: P{N}-* Phase: phase_{N}_{PHASE_NAME} Status: complete "
Output
Return JSON with:
{
"phase": "phase_{N}_{PHASE_NAME}",
"status": "complete",
"deliverables": ["..."],
"artifacts": ["P{N}-*", ...],
"next_phase": "phase_{N+1}_{NEXT_PHASE_NAME}",
"recommendation": "go/no-go"
}
Important
- Follow the phase workflow exactly as defined in the SKILL.md
- Do not skip any steps
- Get all required approvals
- Create all required artifacts
- Update all tracking files
- Leave the project in a clean state
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.
- 3d ago First seen · 94 lines · 11 tokens per session scan A df51aed8c147
lifecycle_phase is a command published in the GitHub repository Harery/OCTALUME (2 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 570 once invoked, about $0.0001 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.
Other commands, from other repositories
dispatch-worker
Run one in-session-agent Worker tick (RFC-0041 §4.3.1).
triage
Score and triage an issue with the RFC-0008 admission composite (PPA + pillar breakdown). Auto-detects GitHub or Backlog.md.
execute-parallel-status
Show live status table of all /ai-sdlc execute-parallel sessions. Reads .ai-sdlc/dispatch/sessions/ and renders task | pane | status | step | PR | heartbeat-age columns. AISDLC-462.
import-spec
Import a spec-kit feature into the backlog. Reads tasks.md and writes one backlog task per upstream entry with specRef: back-references (RFC-0036 Phase 4 / AISDLC-329).
metrics
Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.
audit
Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.