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 enwong93-sketch/devspace-ultra --skill auto-compactgit clone --depth 1 https://github.com/enwong93-sketch/devspace-ultraWrote 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/enwong93-sketch/devspace-ultra/auto-compact)<a href="https://agentmods.dev/skills/enwong93-sketch/devspace-ultra/auto-compact"><img src="https://agentmods.dev/badge/skills/enwong93-sketch/devspace-ultra/auto-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/enwong93-sketch/devspace-ultra/auto-compact"><img src="https://agentmods.dev/badge/skills/enwong93-sketch/devspace-ultra/auto-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 | $0.00005 | $0.00616 |
| Opus 5.5 | $0.00002 | $0.00246 |
| Sonnet 5.5 | $0.00001 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
devspace-auto-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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevSpace Auto Compact
Use this skill when work concerns context pressure, context truncation, compact capsules, backend continuation branches, Goal/Plan continuity, or Auto Compact acceptance.
Product definition
A successful compact operation has two identities:
- UI continuity identity: stable logical key such as
goal:<goalId>, presented to the user as one continuous conversation. - Backend conversation identity: ChatGPT may assign a new conversation ID to the compact continuation branch.
Changing the backend ID is neither success nor failure by itself. The operation is accepted only when all conditions below hold.
Capsule contract
The hidden capsule must preserve:
- Goal objective and success criteria.
- Current user intent and hard constraints.
- Accepted decisions and concise completed-work summary.
- Active Plan frontier, blockers, and next actions.
- Current volatile-state warning and required re-checks.
- Important files, commits, IDs, tests, and evidence.
- PowerMem/handoff references needed to recover durable context.
It must exclude:
- Full conversation mapping.
- Verbatim old transcript.
- Raw tool-output history.
- Hidden chain-of-thought or reasoning content.
- Duplicate progress chatter.
- Expired request/session transport state.
- Credentials and secrets.
Acceptance gates
- Capsule is non-empty and contains the required continuity categories.
- Capsule is within the configured character/token carry budget.
- At least one measurable ratio—exact input tokens, payload bytes, or current-branch message count—is below the maximum carry ratio.
- Target backend conversation ID differs from the source when a continuation branch is used.
- Target contains the hidden capsule and a completed assistant continuation; user-turn mode also contains the original visible user message unchanged.
- Target payload/current branch is materially smaller than the source.
- The hidden source marker, capsule fingerprint, and UI continuity key match.
- Goal, Plan, MCP authority, progress narration, and Host Overlay migrate only after verification.
- No page reload, navigation recovery, synthetic user message, full-history inheritance, or zero-context continuation occurs.
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.
- 1mo ago First seen · 65 lines · 5 tokens per session scan A 2dc78264a8e6
devspace-auto-compact is a skill published in the GitHub repository enwong93-sketch/devspace-ultra (58 stars, last pushed 16d ago), licensed MIT. It adds 5 tokens to every session and 616 once invoked, about $0.0000 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 2026-09-10.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
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.