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/delimit-ai/delimit-mcp-serverWrote 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/delimit-ai/delimit-mcp-server/record)<a href="https://agentmods.dev/commands/delimit-ai/delimit-mcp-server/record"><img src="https://agentmods.dev/badge/commands/delimit-ai/delimit-mcp-server/record/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/delimit-ai/delimit-mcp-server/record"><img src="https://agentmods.dev/badge/commands/delimit-ai/delimit-mcp-server/record.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 | $0.00012 | $0.00225 |
| Opus 5.5 | $0.00005 | $0.00090 |
| Sonnet 5.5 | $0.00002 | $0.00045 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
record scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
When the user invokes /delimit-lite:record (or explicitly asks to record a stated decision or task):
- Check if
delimitis available in PATH, or run vianpx [email protected]:- If
delimitis not installed, inform the user they can install it globally withnpm install -g delimit-cli.
- If
- Save the decision or task by running
delimit remember --tag decision "<content>"ordelimit remember --tag task "<content>"(or the same withnpx [email protected] remember). If arguments were provided ($ARGUMENTS), record them; otherwise use the explicitly stated decision or task. - Include the user's wording and any explicit owner or deadline.
- Ask for essential missing details only when the record would otherwise be misleading. Never infer a commitment or extract one from chat history unless the user asks you to.
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.
- 10d ago First seen · 13 lines · 12 tokens per session scan A d83611057baf
record is a command published in the GitHub repository delimit-ai/delimit-mcp-server (22 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 225 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 2026-11-08.
record compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| recorddelimit-ai/delimit-mcp-server | Command | 22 | yesterday | MIT | A | 12 | Claude Code |
| minutes-ideassilverstein/minutes | Command | 1.6k | today | MIT | A | 48 | Claude Code, OpenCode |
| learnReflexioAI/claude-smart | Command | 796 | today | Apache-2.0 | A | 14 | Claude Code |
| memory-storeverygoodplugins/mcp-automem | Command | 67 | yesterday | MIT | A | 10 | Claude Code |
| analyze-contextRohiRIK/OpenLtm | Command | 30 | 9d ago | MIT | A | 39 | Claude Code |
| cc-memoryTheLobbi/claude | Command | 22 | 19d ago | MIT | A | 0 | Claude Code |
| lians-recallLians-ai/Lians | Command | 17 | 10d ago | Apache-2.0 | A | 19 | Claude Code |