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/fmflurry/settings-opencode/strategic-compactnpx skills add fmflurry/settings-opencode --skill strategic-compactgit clone --depth 1 https://github.com/fmflurry/settings-opencodeWhat 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 | $0.00034 | $0.01404 |
| Opus 5 | $0.00017 | $0.00702 |
| Sonnet 5 | $0.00007 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00140 |
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 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategic Compact (OpenCode) — Autonomous Agent Edition
Purpose
This skill ensures that automatic compaction does not break an agent’s flow.
CRITICAL: compaction is treated as a background checkpoint:
- It can happen at any time near phase boundaries or context pressure.
- The agent must proactively encode durable state so compaction is always safe.
- The agent must not ask the user for confirmation just because compaction might occur.
This skill is about compaction-readiness, not manual compaction.
Operating Rules (Non-Negotiable)
-
Never require user input for compaction.
- Do not ask “Should I compact?” or “Do you want a checkpoint?”
- Assume compaction is automatic and proceed.
-
Never rely on chat history as the only source of truth.
- If something must survive compaction, it must be recorded in files (or a dedicated session log) as durable state.
-
Prefer compaction-safe boundaries.
- A compaction boundary is “safe” only when work is in a stable sub-state (see “Stability Conditions”).
-
Always include evidence.
- Record file paths, commands run, and results (tests/build output summary). If unknown, write “unknown”.
Stability Conditions
Compaction is considered safe when ALL are true:
- Work is not mid-refactor with broken code paths (or the refactor scope is bounded and documented).
- The current goal and plan are written down durably.
- Key decisions/assumptions are explicitly recorded.
- There is a clear next-action checklist.
If conditions are not met, the agent must stabilize first:
- Finish the smallest coherent chunk
- Or save a WIP plan + current diff summary + immediate next steps into durable state
Durable State Checklist (Write This Before Any Likely Boundary)
The agent should maintain a single “durable state” artifact during long work:
./docs/dev/session-log.md(repo-local)
MUST at minimum, record:
- Current goal
- Current phase (research / plan / implement / test / debug)
- Key decisions & constraints
- Files touched / to be touched
- Commands run + results (summary)
- What worked / didn’t work
- Next steps checklist (concrete, executable)
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 · 250 lines · 34 tokens per session scan A bcf08417aaf7
strategic-compact is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed 20d ago), licensed MIT. It adds 34 tokens to every session and 1,404 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…