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/sheawinkler/contextlattice/pigit clone --depth 1 https://github.com/sheawinkler/ContextLatticeWrote 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/sheawinkler/contextlattice/pi)<a href="https://agentmods.dev/agents/sheawinkler/contextlattice/pi"><img src="https://agentmods.dev/badge/agents/sheawinkler/contextlattice/pi.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 | $0.00000 | $0.00425 |
| Opus 5 | $0.00000 | $0.00212 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
pi 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 4d 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
Pi Integration Template
Runtime:
- Orchestrator:
http://127.0.0.1:8075 - Agent profile:
pi - Stable agent id:
pi_agent - Optional install:
brew install pi-coding-agent
For Pi-style conversational agents, keep the instruction lightweight and use ContextLattice as a memory briefing layer, not as a wall of pasted logs. Pi is best treated as an optional scout, summarizer, reviewer, or lightweight refactor runner when the local CLI exists.
ContextLattice does not install Pi automatically. Runner execution is optional and adapter-first: ContextLattice packages context and records lifecycle; the Pi adapter owns local CLI invocation.
Paste into Pi/custom instructions when available:
Use ContextLattice at http://127.0.0.1:8075 for durable memory, scoped recall, and handoff continuity.
Use stable agent_id pi_agent.
Before non-trivial work, run contextlattice context "<task>" --project <project> --pretty. If the CLI is unavailable, continue from local evidence and say degraded-memory mode.
Use contextlattice_agent_adapter state to report idle, working, awaiting_user, blocked, or done when possible.
Checkpoint durable decisions and write a concise handoff before compaction or account/thread transfer.
Do not auto-merge, git push, or treat ContextLattice context as prompt filler.
Post-compaction readback is optional and bounded; use it only to recover prior objective state, not as prompt filler.
Operator workflow:
CONTEXTLATTICE_AGENT_ID=pi_agent contextlattice context "current task" --project contextlattice --pretty
contextlattice resume --project contextlattice --pretty
contextlattice remember "checkpoint summary" --project contextlattice --pretty
contextlattice finish "verified result" --success --project contextlattice --pretty
Optional runner execution:
TASK_AGENT=pi python3 scripts/task_agent_worker.py --task-agent pi --worker-name local-pi-01
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.
- 4d ago First seen · 39 lines · 0 tokens per session scan A 41eef2f76910
pi is an agent published in the GitHub repository sheawinkler/ContextLattice (153 stars, last pushed 8d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 425 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 2026-08-30.
Other agents, from other repositories
ryzome-context
Retrieve and summarize Ryzome canvas or document content for context loading.
notary-archivist
事件记录官 / canon 维护。仅 cc 模板使用；orch / full 由 NeonRP 引擎承担。.
memcp-analyzer
Analyze a MemCP context using the RLM peek-identify-load-analyze pattern. Use proactively when answering questions about stored content without loading it all into the main context.
memcp-entity-extractor
Extract structured entities and relationships from content. Provide the text content to analyze. Use proactively after storing new insights.
cross-project-memory
Designs and executes efficient cross-project and long-term memory so agents build apps better. Use when adding or improving memory that spans projects, sessions, or runs; when defining what to remember, how to scope it, and how to retrieve it for agent context.
cko
Chief Knowledge Officer. Sets knowledge quality standards, directs knowledge-ops for distribution and optimization, owns the guidance registry, manages pace-based distribution cadence.