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 myths-labs/muse --skill strategic-compactgit clone --depth 1 https://github.com/myths-labs/museWrote 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/myths-labs/muse/strategic-compact)<a href="https://agentmods.dev/skills/myths-labs/muse/strategic-compact"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/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/myths-labs/muse/strategic-compact"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/strategic-compact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00037 | $0.00967 |
| Opus 5 | $0.00018 | $0.00483 |
| Sonnet 5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade B, and why
strategic-compact scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Add to your `~/.claude/settings.json`: How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategic Compact Skill
Suggests manual /compact at strategic points rather than relying on arbitrary auto-compaction.
Why Strategic Compaction?
Auto-compaction triggers at arbitrary points:
- Often mid-task, losing important context
- No awareness of logical task boundaries
- Can interrupt complex multi-step operations
Strategic compaction at logical boundaries:
- After exploration, before execution — Compact research, keep plan
- After completing a milestone — Fresh start for next phase
- Before major context shifts — Clear old context before different task
Focus-Aware Compaction (inspired by OpenClaw)
Blind compaction = blind discards. Focus-directed compaction = preserving key information.
Usage: Specify what to preserve when manually compacting.
Scenario: Completed 3 hours of debugging, now starting a new feature
✅ /compact preserve root cause analysis and fix approach, discard trial-and-error debugging
❌ /compact (blind compaction may discard root cause analysis)
Common focus templates:
| Scenario | Focus Directive |
|---|---|
| After debugging | Preserve root cause and fix approach, discard trial-and-error |
| After planning | Preserve final plan and key decisions, discard alternative discussions |
| After code review | Preserve items to change, discard confirmed-OK sections |
| After strategy discussion | Preserve strategic decisions and metrics, discard brainstorming process |
| After multi-file edits | Preserve which files changed and why, discard file content details |
When to Trigger Compaction
| Signal | Action |
|---|---|
| Completed a full milestone | ✅ Good time to compact |
| Switching from exploration to execution | ✅ Good time to compact |
| Debugging complete, starting new feature | ✅ Good time to compact |
| In the middle of multi-step implementation | ❌ Do NOT compact |
| Still analyzing a problem | ❌ Do NOT compact |
/ctx shows 60-70% consumed |
🟡 Consider compacting |
/ctx observes ≥80% pressure |
Save the current Lane, compact if supported, verify and continue |
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 Changed 449465637530
- 10d ago First seen · 105 lines · 37 tokens per session scan B 99f1dfb7596b
strategic-compact is a skill published in the GitHub repository myths-labs/muse (32 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 967 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
context-receipts
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
ijfw-handoff
Session handoff generation and loading. Trigger: session end, context full, /handoff.
ijfw-summarize
Generate optimized project context from codebase scan. Trigger: new project, no CLAUDE.md, /ijfw-summarize.
repo-context-ledger
Record every behavior-changing feature addition, fix, and adjustment as durable, evidence-based repository knowledge, then use that ledger to continue accurately across AI windows, tools, Git collaboration, and pull requests. Use the deterministic runtime to route bounded context, isolate private drafts, publish…
ijfw-status
Use when the user says: 'ijfw status', 'show me the system state', 'what is ijfw doing', or to see the at-a-glance routing / memory / activity banner.