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/LH8PPL/core-memory-kitWrote 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/lh8ppl/core-memory-kit/mechanic)<a href="https://agentmods.dev/agents/lh8ppl/core-memory-kit/mechanic"><img src="https://agentmods.dev/badge/agents/lh8ppl/core-memory-kit/mechanic/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/agents/lh8ppl/core-memory-kit/mechanic"><img src="https://agentmods.dev/badge/agents/lh8ppl/core-memory-kit/mechanic.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 | $0.00062 | $0.00287 |
| Opus 5.5 | $0.00025 | $0.00115 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 (7 stars, last pushed 19d ago), licensed MIT. It adds 62 tokens to every session and 287 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
pm
Technical lead in isolated context: breaks a large job down, assigns it to specialists, integrates what comes back. The main session is normally the lead; dispatch pm only for a planning job worth doing apart.
react-native
React Native expert for repos that are already React Native (new mobile work is Kotlin Multiplatform, owned by app) - Expo or bare workflow, native modules and the platform split, navigation, StyleSheet or Nativewind styling, verified on the iOS simulator and the Android emulator.
dotnet
.NET expert. Consulted before backend to lay out a .NET solution - projects, DI, services, configuration, performance - and dispatched instead of backend when the work is .NET through and through.
frontend
UI implementation to the designer's spec, verified in a real browser.
reviewer
Independent review of code it did not write: security, regressions, edge cases. Reports findings, never fixes them.
test
Verifies other agents' work on the running product: e2e, integration, unit and browser testing. Run once per handover, never per commit.