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 digital-stoic-org/agent-skills --skill instruct-compactgit clone --depth 1 https://github.com/digital-stoic-org/agent-skillsWrote 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/digital-stoic-org/agent-skills/instruct-compact)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/instruct-compact"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/instruct-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 5.1 | $0.00070 | $0.01055 |
| Opus 5 | $0.00035 | $0.00528 |
| Sonnet 5 | $0.00014 | $0.00211 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
instruct-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 7d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruct Compact
Synthesize the current session into a directive block the user copy-pastes into /compact <paste>. The block tells the built-in summarizer what to preserve verbatim, what to compress, and what to drop — so intentional compaction keeps signal and sheds noise.
Output: a fenced block only, printed to terminal. No file written. Target: 250-400 tokens. Speed: 3-5s.
Distinct from /save-context (durable CONTEXT-*-llm.md for resuming later). This is ephemeral steering for compaction now.
When to Use
- User is about to run
/compactand wants to control what survives - Long session nearing auto-compaction; user wants to front-load survival priorities
- Triggers: "instruct compact", "compaction instructions", "steer compact", "prepare compaction"
Instructions
- Read the conversation (last 15-20 messages) — no shell needed unless confirming a file path.
- Synthesize the 8 sections (below). Write directives to the summarizer, not the content itself — e.g. "Preserve exact path
x/y.md", not a copy of the file. Embed a literal only when losing it is expensive (exact paths, the one key decision). - Print the block using the template. Nothing else after it except one line:
Copy the block above into /compact.
The 8 Sections
| Section | Directive to summarizer | Tier |
|---|---|---|
| Goal | State the purpose in 1 sentence; keep verbatim, anchor the summary to it | PRESERVE |
| Hot Files | List exact paths + 3-word role; preserve paths character-for-character | PRESERVE |
| Decisions | Each decision + its rationale; the why is unrecoverable, keep it | PRESERVE |
| Learnings | Non-obvious facts found mid-session (bugs, constraints, gotchas); keep — costly to rediscover | PRESERVE |
| Dead ends | Approaches TRIED and abandoned + why; PRESERVE so they aren't re-attempted. Distinct from Drop (noise): dead ends = negative knowledge worth keeping | PRESERVE |
| Next | 2-4 next actions. IMPORTANT: use heading "Next" — compaction grep-favors next/todo/pending for survival |
PRESERVE |
| Open threads | Unresolved questions / mid-flight work so it isn't dropped | COMPRESS-OK |
| Drop | Name what to discard: verbose tool output, resolved detours, raw logs | DROP |
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.
- 7d ago First seen · 80 lines · 70 tokens per session scan A 3f3d1101c957
instruct-compact is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,055 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.