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/nextnpx skills add endlessblink/master-plan --skill nextgit 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 | $0.00041 | $0.01301 |
| Opus 5 | $0.00020 | $0.00651 |
| Sonnet 5 | $0.00008 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
next 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What's Next?
Analyze MASTER_PLAN.md tasks, score by priority/status, and let the user pick interactively.
Triggers
/master-plan:next- Main command- "what should I work on", "pick a task", "next task", "what's next"
Arguments
| Argument | Filter |
|---|---|
bugs |
Only BUG-XXX tasks |
progress |
Only IN PROGRESS tasks |
planned |
Only PLANNED (backlog) tasks |
review |
Only REVIEW tasks |
active |
IN PROGRESS + REVIEW |
all |
Include DONE tasks |
Example: /master-plan:next bugs or /master-plan:next planned
Workflow
Step 1: Find MASTER_PLAN.md
Search for the plan file in order:
docs/MASTER_PLAN.mdMASTER_PLAN.mdmaster-plan.mddocs/master-plan.md
If not found, tell the user: "No MASTER_PLAN.md found. Run /master-plan:task to create your first task, or create one from the template."
Step 2: Parse Tasks
Read the file and extract tasks from ### headers matching this pattern:
### [optional ~~]TASK-123[optional ~~]: Title (STATUS)
Regex: ^###\s+(~~)?((TASK|BUG|FEATURE|ROAD|IDEA|ISSUE|INQUIRY)-\d+)(~~)?:\s*(.+?)\s*\(([^)]+)\)
For each match, extract:
- ID: e.g.,
TASK-123,BUG-456 - Title: The text after
:and before( - Status: Text in parentheses. Normalize:
- Contains "DONE", "COMPLETE", "FIXED", "✅", or has strikethrough →
DONE - Contains "IN PROGRESS", "🔄" →
IN PROGRESS - Contains "REVIEW", "👀" →
REVIEW - Contains "PAUSED", "⏸️" →
PAUSED - Otherwise →
PLANNED
- Contains "DONE", "COMPLETE", "FIXED", "✅", or has strikethrough →
- Priority: Look in the lines following the header for
**Priority**: P0-P3. Default to P2 if not found.
Step 3: Check for Active Work
Look for IN PROGRESS tasks first — these should be finished before starting new work.
Also check git status:
git status --short
If uncommitted changes exist, mention: "You have uncommitted changes — consider committing or running /master-plan:save first."
Step 4: Sort and Filter
Default sort order (what to START next):
- PLANNED first, then REVIEW, IN PROGRESS, PAUSED, DONE last
- Within same status: P0 → P1 → P2 → P3
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 · 154 lines · 41 tokens per session scan A 0bacdac0ae6a
next is a skill published in the GitHub repository endlessblink/master-plan (27 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 1,301 once invoked, about $0.0002 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
clinpgx-database
Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
coding-tutor
Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
data-artist
Create beautiful data visualizations with mathematical elegance, color theory, and narrative design - the "Data is Beautiful" aesthetic.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.