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/endlessblink/master-plan/savenpx skills add endlessblink/master-plan --skill savegit clone --depth 1 https://github.com/endlessblink/master-planWhat 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 | $0.00053 | $0.00871 |
| Opus 5 | $0.00026 | $0.00436 |
| Sonnet 5 | $0.00011 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
save 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Progress
Save work-in-progress and push to remote repository. Unlike /master-plan:done, this keeps the task status as IN PROGRESS — perfect for:
- Switching machines
- End of session but task not complete
- Before restarting your computer
- Backing up current work
Triggers
/master-plan:save- Main command- "save progress", "switch machine", "end session", "backup work"
Workflow
Step 1: Show Current State
Run these commands to show what changed:
git status
git diff --stat
Display a summary of modified files to the user.
Step 2: Get Task Information
Use AskUserQuestion to gather:
-
Task ID (header: "Task")
- Options: "Tracked task (enter ID)", "No task (just commit)"
-
Update MASTER_PLAN? (header: "Docs")
- Options: "No (just commit)", "Yes (add progress note)"
Then ask in plain text: "What's a brief summary of the progress? (1-2 sentences)"
IMPORTANT: Wait for user to provide the summary before proceeding.
Step 3: Update MASTER_PLAN.md (if requested)
If the user wants to add progress notes:
- Find the task's
###section in MASTER_PLAN.md - Add a progress note with timestamp
Format:
**Progress (YYYY-MM-DD):** [summary of what was done]
Keep status as IN PROGRESS — do NOT change to DONE.
Step 4: Stage Files
Stage all changed files EXCEPT:
.env*files (secrets)node_modules/,__pycache__/,target/,.venv/- Backup directories
- OS files (
.DS_Store,Thumbs.db)
Prefer staging specific files by name over git add -A.
Step 5: Commit
Create a WIP commit:
With task ID:
git commit -m "$(cat <<'EOF'
wip(TASK-XXX): progress summary
Co-Authored-By: Claude <[email protected]>
EOF
)"
Without task ID:
git commit -m "$(cat <<'EOF'
wip: progress summary
Co-Authored-By: Claude <[email protected]>
EOF
)"
Step 6: Push to Remote
git push
Step 7: Output Summary
## Progress Saved
- **Task**: TASK-XXX (or "No task")
- **Summary**: [what was done]
- **Commit**: [short hash]
- **Status**: Still IN PROGRESS
Ready to continue on another machine:
1. `git pull`
2. Continue working on TASK-XXX
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 · 130 lines · 53 tokens per session scan A 728cde721f6e
save is a skill published in the GitHub repository endlessblink/master-plan (27 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 871 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
flow-next-work
Execute a flow-next spec or task end-to-end with worker subagents, gates, and commits. Use when asked to work on, implement, or execute fn-N.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.
kn-commit
Use when committing code changes with proper conventional commit format and verification.
campaign-commit
Choose the correct commit command in a campaign workspace. Use when you are about to commit and need to select camp commit, camp p commit, fest commit, or intentional root pointer sync via camp refs-sync.
commit-work
Verify, stage, and commit a reviewed Codument work step with a focused conventional commit.
walk-commits
Side-route skill for an interactive, commit-by-commit comprehension walkthrough of a finished branch before merge. Use when the person about to merge didn't author the diff — or hasn't internalized it — and needs to understand each commit's intent, riskiest line, deliberate oddities, and what's absent by design, with…