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/msapps-mobile/claude-plugins/make-plannpx skills add MSApps-Mobile/claude-plugins --skill make-plangit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWhat 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 | $0.00086 | $0.00527 |
| Opus 5 | $0.00043 | $0.00264 |
| Sonnet 5 | $0.00017 | $0.00105 |
| Haiku 4.5 | $0.00009 | $0.00053 |
Grade A, and why
make-plan 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.
What it actually says
make-plan: Memory-Grounded Planning
A good plan starts from the current state, not a blank slate. Memory tells you what's been decided, what's blocking progress, and what was left mid-session.
Planning Workflow
1. Load context from memory
# What was done recently?
python3 {SKILL_DIR}/scripts/memory_store.py timeline --hours 168 --limit 30
# What's in progress / blocked?
COWORK_MEM_DB=~/mnt/.claude/.cowork-mem/memory.db \
python3 {SKILL_DIR}/scripts/vector_search.py "in progress blocked next step" --limit 10
# What did the last session summary say?
python3 {SKILL_DIR}/scripts/memory_store.py search "session summary" --type summary --limit 5
2. Check for known errors or constraints
python3 {SKILL_DIR}/scripts/memory_store.py search "error bug blocked" --type error --limit 5
3. Build the plan
Structure the plan as:
- Context: What we know from memory (1-3 bullets, specific)
- Goal: What we're trying to accomplish
- Steps: Numbered, specific, actionable — reference actual files and systems
- Blockers: Known issues from memory that affect the plan
- Open questions: Things we'd need to investigate
4. Save the plan as a decision
python3 {SKILL_DIR}/scripts/memory_store.py add decision \
"Plan: <summary of steps>" --tags "plan,session-goal"
Planning Tips
- Plans built from memory are more accurate than plans from scratch — use it
- Surface blockers from memory explicitly; don't let them be surprises mid-sprint
- If memory has conflicting decisions, flag it for the user to resolve
- Short plans (3-5 steps) are better than exhaustive ones — you can always plan the next thing after
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 · 57 lines · 86 tokens per session scan A 53db7951be42
make-plan is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 6d ago), licensed MIT. It adds 86 tokens to every session and 527 once invoked, about $0.0004 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
change
Track and inspect graph changes, diffs, temporal updates, and the impact of new data on Semantica knowledge graphs.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
scaffold
Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
organize
Repository structure only: directory layout, file placement, naming conventions, and where-does-this-belong decisions. Detects the project's convention, audits files against it, and executes move plans with import-path updates. Never changes code inside files beyond the import updates a move forces; in-file…