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.
git clone --depth 1 https://github.com/RobinNorberg/oh-my-copilotWrote 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/commands/robinnorberg/oh-my-copilot/compact)<a href="https://agentmods.dev/commands/robinnorberg/oh-my-copilot/compact"><img src="https://agentmods.dev/badge/commands/robinnorberg/oh-my-copilot/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/commands/robinnorberg/oh-my-copilot/compact"><img src="https://agentmods.dev/badge/commands/robinnorberg/oh-my-copilot/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 | $0.00014 | $0.00409 |
| Opus 5.5 | $0.00006 | $0.00164 |
| Sonnet 5.5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
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.
This is a copy
97% identical to compact — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
OMC Manual Context Compaction Helper
This command intentionally uses the plugin-scoped name /oh-my-copilot:compact instead of the bare /compact command. Bare /compact is reserved for Claude Code's native compaction command and must not be shadowed by OMC.
OMC cannot invoke Claude Code's built-in /compact from a plugin command: /compact is a native slash command, not a prompt skill, and a prompt-skill call for compact is not a supported handoff. This helper is instruction-only and must not claim that OMC triggers compaction itself.
Dispatch
- Treat this as a request to prepare for manual Claude Code conversation compaction. Do not create a separate OMC summarizer and do not replace existing auto-compress behavior.
- Preserve any user note for the compaction request:
$ARGUMENTS
- Tell the user to run Claude Code's built-in bare
/compactcommand directly. If the note above is non-empty, tell them to include it with/compact. - Before handing off, remind the user that Claude Code's normal
PreCompactlifecycle should run OMC's existing pre-compact hooks (pre-compact, project memory, and wiki preservation) when the native compaction occurs. - Do not invoke a
compactskill, do not attempt to call/compacton the user's behalf, and do not manually summarize the session.
User-facing handoff
Use this wording, adapting only the note text:
OMC prepared the compaction context, but plugin commands cannot trigger Claude Code's native /compact directly. Run this as a bare Claude Code command now:
/compact $ARGUMENTS
Bare /compact remains Claude Code's native command; OMC does not shadow or invoke it.
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 · 36 lines · 14 tokens per session scan A 537246df739e
compact is a command published in the GitHub repository RobinNorberg/oh-my-copilot (5 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 409 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to compact, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
octo-km
Toggle between Dev Work Mode and Knowledge Work Mode.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.specify
Create or update the feature specification from a natural language feature description.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.