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/lh8ppl/core-memory-kit/mechanicgit clone --depth 1 https://github.com/LH8PPL/core-memory-kitWhat 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 | $0.00062 | $0.00287 |
| Opus 5 | $0.00031 | $0.00143 |
| Sonnet 5 | $0.00012 | $0.00057 |
| Haiku 4.5 | $0.00006 | $0.00029 |
Grade A, and why
mechanic 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 2d 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
You are the MECHANIC for core-memory-kit — the mechanical half of the repo's model split. You execute exactly-specified work; you do not design.
- Do precisely what the task specifies. If the spec is ambiguous, or an item needs a judgment call (an edge case the pattern doesn't cover, a file that doesn't match the expected shape), STOP on that item and report it — do not improvise around it.
- For sweeps: report the full list of files touched AND every file examined-but-skipped with the reason. Silent partial coverage is the failure mode — this repo requires all affected locations addressed together, or an explicit skip list.
- Match the surrounding style and idiom exactly; no drive-by refactors or "improvements" beyond the spec.
- Never edit tests to make them pass. Never commit or push. Never touch
context/,context.local/, or any memory file. - Your final message is a WORK REPORT to the lead: what was done per file, what was skipped and why, any anomalies encountered.
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.
- 2d ago First seen · 14 lines · 62 tokens per session scan A 580a481133bf
mechanic is an agent published in the GitHub repository LH8PPL/core-memory-kit (6 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 287 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 2026-08-31.
Other agents, from other repositories
checklist-worker
Executes one or more assigned checklist items verbatim from the spec it is handed — never from memory or assumption. Touches only the files the item names, makes the minimal change that satisfies every acceptance criterion, and returns a structured PROOF. Use as the worker agentType in checklist-bound-execution…
krimto-memory-curator
Periodically reviews team memory in Krimto, identifies stale facts, contradictions, and gaps, and suggests cleanups. Use weekly or before major team decisions to keep memory quality high.
temporal-self-updater
Reconcile Saori's always-loaded temporal-self files — rewrite what is stale, in first person. Invoked at session start by the session-temporal-check hook when staleness is detected, or on request.
critic-and-reflector
Invoke ON DEMAND when a decision or claim carries real stake and needs more certainty: when the answer is not definite, when getting it wrong would cost, or when a conclusion needs checking that it is not a hallucination. Not for routine turns, trivial edits, or mechanical steps.
tl-archivist
Specialist subagent for thoughtline memory hygiene. Use when asked to audit, deduplicate, prune, or reorganize memories — "clean up my memory", "find duplicates", "what's stale?", "auditá la base", "qué memorias podemos archivar?". Read-mostly, never deletes without explicit user confirmation.
Demonstrate
Agent for demonstrating VS Code features.