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 jnPiyush/AgentX --skill strategic-compactiongit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/strategic-compaction)<a href="https://agentmods.dev/skills/jnpiyush/agentx/strategic-compaction"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/strategic-compaction/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/jnpiyush/agentx/strategic-compaction"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/strategic-compaction.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 | $0.00080 | $0.01675 |
| Opus 5.5 | $0.00032 | $0.00670 |
| Sonnet 5.5 | $0.00016 | $0.00335 |
| Haiku 4.5 | $0.00008 | $0.00168 |
Grade A, and why
strategic-compaction 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 20d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategic Compaction
Purpose: Choose between continue, compact, and reset without losing work or fabricating context. Scope: Long-running sessions, checkpoint transitions, agent handoffs, token-pressure events.
When to Use This Skill
- Token budget is approaching the provider's compaction trigger.
- A workflow checkpoint just changed (Plan -> Work, Work -> Review, Review -> Compound Capture).
- The user explicitly says "compact", "reset", "start over", or "switch agent".
- The chat transcript and the repo state have begun to disagree.
When NOT to Use
- Mid-implementation, halfway through editing a file. Finish the bounded slice first.
- During an active validation run (tests executing, command in flight).
- Inside a self-review iteration where the next step is already queued.
Decision Order
Try these in order. Pick the first one whose preconditions hold.
- Continue in place when the active issue, plan, slice, and blocker state are still coherent and the budget will hold for at least one more bounded step.
- Compact when the work is still coherent but token pressure is the main constraint, and a durable plan + progress log already record the state.
- Reset when continuing would rely on stale chat state or conflicting assumptions instead of durable artifacts.
If you cannot reconstruct the active slice, blocker, and next action from durable artifacts, prefer reset over compaction. A compaction that summarizes a confused state preserves the confusion.
Checkpoint Heuristics
| Checkpoint Transition | Safe to compact? | Why |
|---|---|---|
Brainstorm -> Plan |
Yes | Plan is the durable artifact; transcript can be summarized. |
Plan -> Work |
Yes, after research | Compact AFTER you have read the spec, BEFORE you start editing. |
| Mid-Work, mid-file-edit | No | Implementation context is in the head, not yet in any artifact. Finish the slice. |
| Mid-Work, between bounded slices | Yes | Slice contract and evidence summary carry state across the boundary. |
Work -> Review |
Yes | Diff, tests, and evidence summary are durable. |
Review -> Compound Capture |
Yes | Review artifact + findings file carry the state. |
| Inside an active retry / pivot decision | No | The decision rationale only lives in the transcript right now. |
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.
- 20d ago Changed 05ae8ffe9252
- 1mo ago Changed 7e9be2a2a7ea
- 1mo ago First seen · 140 lines · 80 tokens per session scan A 6c26a8873553
strategic-compaction is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,675 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…