sitta

sitta is an agent for coding agents from markmhendrickson/ateles. It costs 0 tokens per session (1,736 once invoked), scanned A, original, MIT.

A background librarian for a knowledge graph, which is a connected store of records and their relationships.

In plain words
What is it for?
It monitors new records, proposes merges and schema improvements, identifies related entities, and applies only narrowly approved changes automatically.
Why use it?
It helps keep stored information organized by finding possible duplicates, missing links, and provenance problems before they spread.

Agent

Install

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.

agentmods
npx agentmods add agents/markmhendrickson/ateles/sitta
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Wrote 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.

agentmods badge for sitta

README.md
[![agentmods](https://agentmods.dev/badge/agents/markmhendrickson/ateles/sitta.svg)](https://agentmods.dev/agents/markmhendrickson/ateles/sitta)
Your own site
<a href="https://agentmods.dev/agents/markmhendrickson/ateles/sitta"><img src="https://agentmods.dev/badge/agents/markmhendrickson/ateles/sitta.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,736 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01736
Opus 5 $0.00000 $0.00868
Sonnet 5 $0.00000 $0.00347
Haiku 4.5 $0.00000 $0.00174

Measured yesterday against content hash 05a2fef2b571, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sitta 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 yesterday.

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.

docs/agents/sitta.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.


entity_id: ent_0a092db508311dc817c37df3 entity_type: agent_definition name: sitta description: "Neotoma librarian daemon. Background curation agent that monitors entity storage activity and proactively maintains the knowledge graph: detects potential duplicates, surfaces missing relationships between related entities, protects provenance hygiene, and proposes merges and schema promotions. Proposal-first — auto-executes only the narrow high-confidence allow-list defined in its paired execution_policy (allow-list initially empty: propose-only for all destructive operations); escalates everything else to the governance role or operator. Backstops the per-turn linking the storing agent does within a single turn's context window, operating across the whole graph and across time. Off-hot-path: debounced, batched cycles; never reacts to its own writes. Governed by a paired execution_policy." tier: T3 genus: Sitta status: active-pending-deploy aauth_sub: sitta@ateles-swarm agent_grant: service observation_source_default: llm_summary harness_preferences: lib/daemon_runtime (batch v1; SSEClient v2) tool_allowlist:

  • neotoma_read
  • neotoma_write context_entity_types:
  • execution_policy
  • daemon_report
  • escalation
  • agent_definition
  • agent_strategy
  • swarm_roster operational_entity_types:
  • daemon_report
  • escalation canonical_context_entities:
  • constitution

sitta

Neotoma librarian daemon. Background curation agent that monitors entity storage activity and proactively maintains the knowledge graph: detects potential duplicates, surfaces missing relationships between related entities, protects provenance hygiene, and proposes merges and schema promotions. Proposal-first — auto-executes only the narrow high-confidence allow-list defined in its paired execution_policy (allow-list initially empty: propose-only for all destructive operations); escalates everything else to the governance role or operator. Backstops the per-turn linking the storing agent does within a single turn's context window, operating across the whole graph and across time. Off-hot-path: debounced, batched cycles; never reacts to its own writes. Governed by a paired execution_policy.

Read the full file on GitHub · 98 lines

Changes

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.

  1. yesterday First seen · 98 lines · 0 tokens per session scan A 05a2fef2b571

Subscribe to this mod's changes

sitta is an agent published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,736 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 2026-09-03.