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/anilcancakir/claude-code-plugins/strategic-compactnpx skills add anilcancakir/claude-code-plugins --skill strategic-compactgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWrote 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/anilcancakir/claude-code-plugins/strategic-compact)<a href="https://agentmods.dev/skills/anilcancakir/claude-code-plugins/strategic-compact"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code-plugins/strategic-compact.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00684 |
| Opus 5 | $0.00029 | $0.00342 |
| Sonnet 5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
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 5d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategic Compact
Intelligent context management that suggests compaction at optimal moments.
Core Principle
Manual compaction at strategic points > Auto-compaction at arbitrary points
Auto-compact triggers at context limits, often mid-task. Strategic compaction preserves context through logical phases and compacts at natural transition points.
When to Suggest Compaction
Optimal Compaction Points
| Trigger | Reason |
|---|---|
| Exploration complete, implementation starting | Exploration context rarely needed for coding |
| Milestone completed | Clean slate for next phase |
| Plan finalized and documented | Plan captured, context can reset |
| Debug session resolved | Debug traces clutter future work |
| Switching to unrelated task | Previous context not relevant |
| 50+ tool calls in session | Accumulated context likely stale |
Avoid Compaction During
| Scenario | Why |
|---|---|
| Mid-implementation | Loses code context and decisions |
| Active debugging | Loses diagnostic information |
| Incomplete task | May need earlier context |
| Code review in progress | Loses review thread |
Compaction Options
/compact (Quick)
- Built-in summarization
- Frees context immediately
- May lose some nuance
/handoff (Recommended for complex work)
Creates HANDOFF.md with:
- Current goal and progress
- What worked / what didn't
- Next steps
- Key decisions made
Then start fresh with: > HANDOFF.md
/clear (Fresh start)
- Complete reset
- Best when switching tasks entirely
Phase Detection Patterns
Detect phase transitions by monitoring:
EXPLORATION → IMPLEMENTATION
- Many Read/Grep/Glob calls → Edit/Write calls starting
- Questions answered → Code being written
IMPLEMENTATION → TESTING
- Edit/Write heavy → Bash(test) calls
- Feature code done → Verification starting
DEBUGGING → RESOLUTION
- Error investigation → Fix confirmed working
- Multiple attempts → Success achieved
Automatic Behavior
This skill works with hooks that:
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.
- 5d ago First seen · 112 lines · 58 tokens per session scan A 3bfefbf7d892
strategic-compact is a skill published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 58 tokens to every session and 684 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 2026-08-31.
Other skills, from other repositories
system-boot
Auto-activating session startup - reads memory, orients Claude, announces status. Triggers on session start or when user says "continue", "weiter", "resume".
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
codify-lesson
Detect recurring P2/P3 audit patterns across recent rounds and promote them into lesson cards. Use after round boundaries or when repeated findings appear.