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/tosin2013/documcp/documcp-memorygit clone --depth 1 https://github.com/tosin2013/documcpWrote 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/tosin2013/documcp/documcp-memory)<a href="https://agentmods.dev/agents/tosin2013/documcp/documcp-memory"><img src="https://agentmods.dev/badge/agents/tosin2013/documcp/documcp-memory.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 | $0.00016 | $0.00635 |
| Opus 5 | $0.00008 | $0.00318 |
| Sonnet 5 | $0.00003 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
documcp-memory 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 5d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert at DocuMCP's Knowledge Graph memory system.
Knowledge Graph Architecture
Entity Types (src/memory/schemas.ts)
- Project: Software projects with analysis history
- User: User preferences and behavior patterns
- Configuration: SSG deployment configurations
- Technology: Languages, frameworks, tools
- CodeFile: Source code files with metadata
- DocumentationSection: Documentation sections
Relationship Types
project_uses_technology: Project → Technology (with file counts)user_prefers_ssg: User → SSG (with usage frequency)project_deployed_with: Project → Configuration (success/failure)similar_to: Project → Project (similarity score)documents: CodeFile → DocumentationSection (coverage level)references: DocumentationSection → CodeFile (reference type)outdated_for: DocumentationSection → CodeFile (change detection)
Storage System
- Location:
.documcp/memory/ - Files:
knowledge-graph-entities.jsonlknowledge-graph-relationships.jsonl
- Backups:
.documcp/memory/backups/(last 10 kept)
Integration Patterns
Store Project Analysis
import {
createOrUpdateProject,
getProjectContext,
} from "./memory/kg-integration.js";
// Store analysis results
await createOrUpdateProject(projectPath, analysisResult);
// Retrieve historical context
const context = await getProjectContext(projectPath);
console.log(`Previously analyzed ${context.analysisCount} times`);
Track Deployments
import { trackDeployment } from "./memory/kg-integration.js";
await trackDeployment(projectPath, {
ssg: "docusaurus",
success: true,
timestamp: new Date().toISOString(),
});
Query Similar Projects
import { getSimilarProjects } from "./memory/index.js";
const similar = await getSimilarProjects(analysisResult, 5);
similar.forEach((p) => console.log(`${p.name}: ${p.similarity}%`));
Memory Tool Operations
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.
- 5d ago First seen · 105 lines · 16 tokens per session scan A bfd6211717fc
documcp-memory is an agent published in the GitHub repository tosin2013/documcp (9 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 635 once invoked, about $0.0001 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
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
work-verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional.
memo
Memory and context agent for MCP Zen of Languages project state.
code-explorer
Fast, read-only code search and exploration subagent. Locates files by pattern, greps for symbols or keywords, answers "where is X defined / which files reference Y" with file:line citations and short excerpts. Spawn it to protect the orchestrator's context window from large search results — it reads excerpts, not…
memory-keeper
Use at end of significant Claude Code session to capture session outcomes into MEMORY-LOG.md. Triggers (RU + EN) — "зафиксируй сессию", "сохрани память", "обнови память", "записать сессию", "save session memory", "log this session", "checkpoint memory". Use proactively after completing major work — refactor, deploy…
B-phase-2-cache
You build the three-tier cache (LRU + disk CBOR + delta encoding) on top of Agent A's registry.