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 skills add mshadmanrahman/pm-pilot --skill strategic-compactgit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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/skills/mshadmanrahman/pm-pilot/strategic-compact)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/strategic-compact"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/strategic-compact/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/strategic-compact"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/strategic-compact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00015 | $0.00508 |
| Opus 5 | $0.00008 | $0.00254 |
| Sonnet 5 | $0.00003 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
strategic-compact 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategic Compact
Proactively manage context window to prevent degraded performance in long sessions.
When to Use
- Context usage exceeds 60%
- After completing a major planning phase
- After finishing implementation, before review
- Before starting a fundamentally different task
- When responses start feeling slower or less precise
Procedure
-
Assess Context State
- Estimate current context consumption
- Identify which content is load-bearing vs stale
-
Identify Compaction Point Suggest compaction at natural milestones:
- After planning: decisions locked, plan documented
- After implementation: code committed, tests passing
- Before review: implementation complete, shifting to review mode
- After triage: results documented, moving to fixes
-
Preserve Key State Before suggesting
/clear, ensure these are persisted:- Active task and status in
tasks/todo.md - Key decisions in handoff doc or
tasks/lessons.md - Any uncommitted work is committed or stashed
- File paths of actively-edited files
- Active task and status in
-
Suggest Compaction Output:
Context check: ~{percent}% used Milestone: {what was just completed} Recommendation: {compact now / safe to continue / approaching limit} Before /clear: - [ ] Handoff doc written - [ ] Work committed - [ ] Todo updated -
Post-Compaction Recovery After
/clear, usesession-initskill to restore context.
Output Format
Context check: ~65% used
Milestone: Implementation phase complete
Recommendation: Good time to compact before code review
Before /clear:
- [ ] Handoff doc written
- [ ] Work committed (3 files)
- [ ] Todo updated
Rules
- Never force compaction; always suggest
- Never compact mid-task; wait for a milestone
- Always write handoff doc before suggesting /clear
- Err on the side of compacting earlier rather than later
- The last 20% of context window produces degraded output
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.
- 9d ago First seen · 80 lines · 15 tokens per session scan A 6c412cce0ee7
strategic-compact is a skill published in the GitHub repository mshadmanrahman/pm-pilot (20 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 508 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 2026-08-30.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or…
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
lat-md-knowledge-graph
Design or audit a repo-local markdown knowledge graph with wiki links, source-code backlinks, drift checks, and searchable sections. Use when AGENTS.md/CLAUDE.md is too flat for a large codebase or when a custom harness needs durable structured project memory.
analyze-codebase
Run comprehensive PLG analysis on a codebase to detect tech stack, existing growth features, and revenue opportunities. Use when the user says "analyze", "scan", "audit codebase", or "find growth opportunities".