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/paulbreuler/limps/005-integration-migrationgit clone --depth 1 https://github.com/paulbreuler/limpsWhat 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 | $0.00000 | $0.01862 |
| Opus 5 | $0.00000 | $0.00931 |
| Sonnet 5 | $0.00000 | $0.00372 |
| Haiku 4.5 | $0.00000 | $0.00186 |
Grade A, and why
005-integration-migration 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.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 005: CLI Interface
Objective
Build the primary CLI interface. CLI is the source of truth. MCP and Obsidian wrap CLI.
Context
limps CLI (the actual intelligence)
↑
│ wraps
↓
MCP Server (for AI that can't shell out)
↑
│ also wraps
↓
Obsidian Plugin (human UI)
All commands output JSON when --json flag is passed, making MCP wrapping trivial.
Tasks
1. Command Structure
limps graph
├── reindex [--plan <id>] [--incremental]
├── health [--json]
├── check <type> [--json]
├── watch [--on-conflict <target>] [--url <webhook>]
├── search <query> [--top <k>] [--json]
├── trace <entity> [--direction up|down|both] [--depth <n>] [--json]
├── entity <canonical-id> [--json]
├── overlap [--plan <id>] [--threshold <n>] [--json]
└── suggest <type> [--json]
2. Health Command (src/cli/commands/graph/health.ts)
import { Command } from 'commander';
import { ConflictDetector } from '../../watch/detector';
export const healthCommand = new Command('health')
.description('Run full health check on knowledge graph')
.option('--json', 'Output as JSON')
.action(async (options) => {
const detector = new ConflictDetector(storage);
const conflicts = detector.detectAll();
if (options.json) {
console.log(JSON.stringify({ conflicts, stats: storage.getStats() }, null, 2));
return;
}
// Human-readable output
if (conflicts.length === 0) {
console.log('✅ No conflicts detected');
} else {
for (const c of conflicts) {
const icon = c.severity === 'critical' ? '🚨' : c.severity === 'warning' ? '⚠️' : 'ℹ️';
console.log(`${icon} ${c.type}: ${c.message}`);
if (c.suggestion) console.log(` 💡 ${c.suggestion}`);
}
}
const stats = storage.getStats();
console.log(`\n📊 Graph: ${stats.totalEntities} entities, ${stats.totalRelations} relationships`);
});
3. Search Command (src/cli/commands/graph/search.ts)
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 · 274 lines · 0 tokens per session scan A 0f244f74a4d9
005-integration-migration is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,862 tokens. 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
monitor
Reviews code for correctness, standards, security, and testability (MAP).
evaluator
Evaluates solution quality and completeness (MAP).
predictor
Predicts consequences and dependency impact of changes (MAP).
task-decomposer
Breaks complex goals into atomic, testable subtasks (MAP).
actor
Generates production-ready implementation proposals (MAP).
documentation-reviewer
Reviews technical documentation for completeness, external dependencies, and architectural consistency.