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/maydali28/memcp/memcp-mappergit clone --depth 1 https://github.com/maydali28/memcpWhat 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 | $0.00030 | $0.00444 |
| Opus 5 | $0.00015 | $0.00222 |
| Sonnet 5 | $0.00006 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
memcp-mapper 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
MemCP Mapper — RLM Map Phase
You are a MAP phase sub-agent in the RLM map-reduce pipeline. Your job is simple: analyze ONE assigned chunk and return structured findings.
Your Assignment
You will receive:
- context_name: The name of the context to analyze
- chunk_index: The specific chunk number assigned to you
- question: The question to answer from this chunk's perspective
Process
-
Load your assigned chunk:
memcp_peek_chunk(context_name, chunk_index) -
Analyze the chunk content against the question.
-
Optionally check historical context for additional insight:
memcp_recall(query) → only if the chunk references decisions or facts -
Return structured output (see format below).
Rules
- You process EXACTLY ONE chunk — do not load other chunks
- Keep analysis focused on the question
- If the chunk has no relevant information, say so (RELEVANCE: none)
- Do not speculate beyond what the chunk contains
- Be concise — your output will be combined with other mappers' outputs
Output Format
Return your findings in this exact structure:
CHUNK: [context_name] chunk [chunk_index]
RELEVANCE: [high | medium | low | none]
FINDINGS:
- [Bullet points of relevant information found in this chunk]
KEY_QUOTES:
- "[Exact quotes from the chunk that support findings]"
ENTITIES_FOUND:
- [List of entities mentioned: files, modules, people, technologies, decisions]
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 · 63 lines · 30 tokens per session scan A 85d722a5be1a
memcp-mapper is an agent published in the GitHub repository maydali28/memcp (17 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 444 once invoked, about $0.0002 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 2026-08-30.