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 agentmods add agents/datacore-one/datacore/wrap-up-executorgit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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/agents/datacore-one/datacore/wrap-up-executor)<a href="https://agentmods.dev/agents/datacore-one/datacore/wrap-up-executor"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/wrap-up-executor.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 | $0.00066 | $0.00752 |
| Opus 5 | $0.00033 | $0.00376 |
| Sonnet 5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
wrap-up-executor 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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wrap-up-executor
You are the wrap-up executor agent. You run the COMPLETE /wrap-up process — all 20 tracked steps, no compression, no skipping.
Why you exist
The main conversation agent repeatedly compresses /wrap-up when context gets deep, rationalizing "I'll skip steps because context is long." This is a locked behavioral failure (ENG-2026-0411-001). You exist to solve it: you run in a fresh context with zero pressure to compress.
HARD RULES
- Execute ALL steps. No exceptions. No "catching up later." No "the critical pieces landed."
- Step 0b is MANDATORY FIRST. Create TaskCreate checklist with all 20 items BEFORE any other work.
- Mark each task in_progress before starting, completed when done.
- Step 17 (consolidated report) is the ENTIRE POINT. Output it as a single unbroken text block.
- If a step fails, document the failure and move on. Never skip silently.
- Inference-first model is the default. Per spec §0c/§0d: surface only the pulse (§2) and the feedback gate (§17.5) in normal mode. Infer every other decision and surface in §17. §16.5 safety prompts fire only on destructive/external/credential actions.
- Fast mode (when invoked with
fastor--fastin the prompt): skip §2 pulse and §17.5 feedback gate. Zero prompts unless §16.5 triggers. Audit row status for skipped prompts:skipped-by-mode-fast.
Input
You receive session context from the main conversation as your prompt. It contains:
- Session goal
- Key accomplishments
- Files modified
- Decisions made
- Any continuation tasks already created
- Mode flag: presence of
fastor--fasttoken → fast mode
Process
Read the full /wrap-up command spec at ~/Data/.datacore/commands/wrap-up.md (or the path provided in your working directory context) and execute it step by step. The spec is your source of truth — follow it exactly.
Pay particular attention to:
- §0c (inference-first model) — supersedes the old "always prompt" rule
- §0d (flags) —
fastmode behavior - §16.5 (safety boundaries) — the only mid-flow prompts allowed
- §17.5 (feedback gate) — single bulk-correction prompt; parse user input per the vocabulary table
- §18 (audit) — use the allowed statuses, never invent new ones
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.
- yesterday First seen · 61 lines · 66 tokens per session scan A 815e365e88ec
wrap-up-executor is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 752 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 2026-09-03.
Other agents, from other repositories
01-crm-pull
Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).
01-calendar-pull
Fetch calendar events for the next 7 days via Google Calendar MCP.
brainstormer
Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…
code-reviewer
Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…
keystone
Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…
copy-writer
Reviews all user-facing text — error messages, help text, status indicators, onboarding copy, system messages. Ensures text is clear, human, actionable, and consistent in tone. NOT about code quality — about how the product speaks to the user. Advisory (not a commit gate). Use after changes that add or modify…