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 LogicLabsAI/ultramemory-mcp --skill checklist-bound-executiongit clone --depth 1 https://github.com/LogicLabsAI/ultramemory-mcpWrote 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/logiclabsai/ultramemory-mcp/checklist-bound-execution)<a href="https://agentmods.dev/skills/logiclabsai/ultramemory-mcp/checklist-bound-execution"><img src="https://agentmods.dev/badge/skills/logiclabsai/ultramemory-mcp/checklist-bound-execution/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/logiclabsai/ultramemory-mcp/checklist-bound-execution"><img src="https://agentmods.dev/badge/skills/logiclabsai/ultramemory-mcp/checklist-bound-execution.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 | $0.00154 | $0.01634 |
| Opus 5 | $0.00077 | $0.00817 |
| Sonnet 5 | $0.00031 | $0.00327 |
| Haiku 4.5 | $0.00015 | $0.00163 |
Grade A, and why
checklist-bound-execution 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checklist-Bound Execution
A harness for fanning checklist / plan items out to spawned agents WITHOUT drift. Use it any time two or more agents execute items from a shared plan and "did the agent actually do its exact job?" matters.
Why this exists (read first)
Spawned agents (Workflow agents, Task subagents) start with a FRESH, isolated context. They do not
see the conversation, the plan, or your intent unless it is handed to them. When the assignment is
vague — or worse, fails to arrive (the Workflow args global is unreliable and has come through as
undefined) — the agent reconstructs the task from whatever it can read and IMPROVISES. That is the
root cause of drift, not "lack of discipline."
Enforcement is therefore NOT a single instruction. It is four mechanisms together:
- Determinism of assignment — each agent receives its item VERBATIM, embedded in its prompt.
- Structured proof — each agent must return a schema-validated completion record (validated at the tool layer, so it cannot hand-wave; the runtime retries on mismatch).
- Independent verification — a separate, read-only agent re-checks each item against its acceptance criteria, adversarially, and can FAIL it.
- Loop-back — a failed item is sent back to a worker to fix, then re-verified, up to a bound.
A skill alone is advisory. This skill works because it pairs the procedure (here) with the Workflow
script's deterministic control flow + structured-output schemas + a verifier stage. An optional
SubagentStop hook can add a hard, model-can't-skip gate; this skill does not require one.
The non-negotiable invariants
- One item, one job. A worker does ONLY its assigned item(s). It touches ONLY the files the item
names. Anything outside scope is a
deviation— reported, not silently done. - Verbatim, not from memory. The item's
specandacceptance_criteriaare the source of truth. If they conflict with the worker's prior assumptions, the item wins. If the item is ambiguous or impossible as written, the worker returnsstatus: "blocked"with the reason — it does NOT guess. - No
args, no filesystem in the script. Workflow scripts cannot read files or rely onargs. Embed the checklist as a literal in the script (seereferences/workflow-template.js). Workers may ALSO be given the checklist file path to re-read as a cross-check. - Verifier is read-only and adversarial. It tries to prove the item is NOT done. It cannot edit (so it cannot bias itself by fixing). Default to FAIL when evidence is missing.
- Done means verified. An item is complete only when its verifier verdict is
pass: true.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 106 lines · 154 tokens per session scan A 8a7724a2c5ce
checklist-bound-execution is a skill published in the GitHub repository LogicLabsAI/ultramemory-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 154 tokens to every session and 1,634 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
dashboard
Open OwnMem Console, the local dashboard for this repository's memory. Use when the user asks to open the dashboard, see memory metrics, check adoption or recall quality, or set up the optional embedding lane. Requires a repository initialized with the dashboard layer.
recall
Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
memory-write
Captures a durable fact to project memory through the kit's safe write path (PoisonGuard secret/injection screening + home-path sanitization + dedup + conflict detection) — preferring the cmk MCP tools (mkremember / mkforget / mktrust) when connected, falling back to the cmk CLI. Use when the user says "remember…
bootstrap
Scaffolds the core-memory-kit directory structure (context/, scripts/, cron/jobs/) into the current project. Idempotent — never overwrites existing files. Run once per project after installing the plugin. Use when the user says "bootstrap the memory system", "set up memory here", or "scaffold the memory kit".
brain-compiler
Generate or refresh SAN using the canonical contract and Agent Brain tools.