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 shennawardana23/skillme --skill strategic-compactgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/strategic-compact)<a href="https://agentmods.dev/skills/shennawardana23/skillme/strategic-compact"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/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/shennawardana23/skillme/strategic-compact"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/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 | $0.00103 | $0.01334 |
| Opus 5 | $0.00051 | $0.00667 |
| Sonnet 5 | $0.00021 | $0.00267 |
| Haiku 4.5 | $0.00010 | $0.00133 |
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 8d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategic Compact
Manual /compact at a chosen point beats compaction triggered
automatically at an arbitrary token threshold, because automatic
compaction has no notion of where in the task you actually are — it can
fire mid-debugging and discard the exact state (which hypotheses were
already tried, what the last error looked like) the next step needs.
Compacting deliberately, at a logical boundary, keeps what matters and
discards what doesn't.
The decision, by phase transition
| Transition | Compact? | Why |
|---|---|---|
| Research → planning | Yes | Research context is bulky; the plan is the distilled output worth keeping |
| Planning → implementation | Yes | Once the plan is written down (a todo list or a file), free the context it took to reach it |
| Implementation → testing | Maybe | Keep if tests reference details from the code just written; compact if switching focus entirely |
| Debugging → next feature | Yes | Debug traces and dead-end hypotheses pollute context for unrelated work |
| Mid-implementation | No | Losing variable names, file paths, and partial state mid-task is costly and hard to reconstruct |
| After a failed approach, before trying another | Yes | Clear the dead-end reasoning trail before starting the next attempt with a clean slate |
The pattern across all of these: compact when the next step doesn't need the reasoning process that got you here, only its output. Don't compact when the next step is a continuation of the same reasoning.
What actually survives compaction
Compacting isn't all-or-nothing — some things persist regardless, which should shape what you do before compacting:
| Persists | Lost |
|---|---|
| Written instructions/config files | Intermediate reasoning and analysis |
| A task list written to a file or tracked externally | Contents of files you read earlier but didn't need to re-read |
| Anything written to disk | Multi-step conversational context |
| Git history (commits, branches) | Tool-call history and counts |
| Files on disk generally | Nuanced preferences stated verbally but never written down |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is 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.
- 8d ago First seen · 115 lines · 103 tokens per session scan A 3407a045804b
strategic-compact is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,334 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
usage-audit
Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.
token-saver
Skill to implement token saving scheme, concise, and focused on essential changes / Skill untuk menerapkan skema penghematan token, ringkas, dan fokus pada perubahan esensial tanpa basa-basi.
obsidian-todo-collector
An Obsidian note-organising tool that scans dated notes for unfinished events and plans, then gathers them into one tracking document. Obsidian is an app for storing linked notes as Markdown files.
persistent-memory
Persists context across conversations as plain markdown so every future session can enrich a topic-scoped memory (e.g. parenting, relationship-anna, work-history, project-acme). Four operations: write (extract candidates, resolve as ADD / UPDATE / DELETE / NOOP per Mem0), read (load a ≤ 200-line INDEX; fetch detail…
changelog
Generates a personal markdown changelog of merged or closed pull requests authored by the current user and Linear tickets the user closed or worked on, over a configurable window (default 7 days), grouped by feature area (e.g. Dashboards, Agent0). Inputs sourced from gh search prs --author=@me and the Linear MCP. Use…