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 skills/leaf76/session-collab-mcp/plan-completenpx skills add leaf76/session-collab-mcp --skill plan-completegit clone --depth 1 https://github.com/leaf76/session-collab-mcpWhat 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 | $0.00015 | $0.00522 |
| Opus 5 | $0.00008 | $0.00261 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
plan-complete 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Completion
Record that a protected plan has been completed. The current v2 API does not expose direct plan status transitions, so completion is tracked via working memory while the protected plan entry remains available.
When to Use
- All tasks in the plan have been implemented
- User confirms the plan is complete
- Moving on to a new phase of work
Required Actions
Step 1: Identify the Plan
Ask the user or check the session's protected plans:
collab_protect with action="list" and session_id
Step 2: Verify Completion
Before recording completion, verify:
- All todo items are done
- Code changes are committed
- Tests pass (if applicable)
Step 3: Save Completion Summary
Call collab_memory_save with:
session_id: Your session IDcategory:"state"key: A stable key such asplan_complete:<file_path>content: Brief summary of what was achievedpriority:80pinned:true
Step 4: Confirm with User
Display the result and ask if they want to:
- Keep the plan file protected - Leave the protection entry as-is
- Clear the completion note later - Use
collab_memory_clearwhen the note is no longer needed - Delete the plan file - Remove from filesystem only with explicit confirmation
Step 5: Optional Cleanup
If the user no longer needs the completion note, call collab_memory_clear with:
session_id: Your session IDkey: The completion key you saved in Step 3
Output Format
### Plan Completion Recorded
| Item | Value |
|------|-------|
| Plan | [plan title] |
| File | [file path] |
| Status | Completion recorded |
### Summary
[What was achieved]
### Next Steps
- Keep the plan protected or delete it explicitly later
- Clear the completion note when it is no longer useful
Notes
- The protected plan entry remains available through
collab_protect - Completion state is recorded in working memory, not in a separate plan-status tool
- Plans are never auto-deleted, only manually by user request
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 · 81 lines · 15 tokens per session scan A fbad072e7200
plan-complete is a skill published in the GitHub repository leaf76/session-collab-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 522 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 skills, from other repositories
claude-code-dmwork
Connect to DMWork messaging platform as an AI bot via the OpenClaw DMWork adapter plugin.
meeting
Use for /meeting, /meeting sync, /meeting backfill, or a search term — adaptively analyzes a Granola meeting into decisions, findings, actions, and continuity in shared memory.
reflect
Use when the user says 'we decided', 'I realized', or 'that's a pattern' — captures decisions, findings, or patterns in shared memory. Not a private half-baked thought (/note) or cross-referencing (/deep-reflect).
activity
See what is happening across the team — recent sessions, handoffs, quests, and open PRs. Use for /activity, catching up after time away, or checking team-wide status at a glance.
dark-mode
Use when generating or modifying any visual output that renders in a browser or artifact viewer: HTML pages, CSS, React SSR components, Egregore artifacts, markdown renderers, web components, design-system tokens, Tailwind themes, or standalone demos. Triggers on requests involving dark mode, theme toggles, color…
dashboard
See your recent sessions, open handoffs, and current work at a glance. Use for /dashboard, checking your personal status — not the team-wide view (/activity).