bearing AGENTS.md

Repository instructions for Bearing, a tool that breaks coding work into tasks and coordinates their execution. They also describe its history handling, evaluation tools, and connections to AI providers.

In plain words
What is it for?
Use them when changing Bearing, running its evaluations, comparing orchestration approaches, or working on its task queue, agents, retrievers, and status files.
Why use it?
They give a coding agent the project structure and rules it needs to work consistently. They explain how to evaluate task coordination, context compression, and history retrieval.

Instructions file for CodexOpenCode

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 instructions/rocketvish/bearing/agents-md
Clone the repo
git clone --depth 1 https://github.com/rocketvish/bearing

Made for: Codex, OpenCode.

Per session 1,438 This file is loaded in full into every session.
When invoked 1,438 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01438 $0.01438
Opus 5 $0.00719 $0.00719
Sonnet 5 $0.00288 $0.00288
Haiku 4.5 $0.00144 $0.00144

Measured 2d ago against content hash 60827cc69883, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bearing AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `agent.py` -- Tool-use agent via provider adapters (OpenAI Responses or Anthropic Messages, urllib/no SDK), with prompt caching + reasoning effort
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bearing - Task Orchestrator for Codex

Architecture

  • bearing.py -- CLI entry point + orchestration loop (run_orchestrator, propagate_context)
  • executor.py -- Prompt assembly (assemble_prompt) + CLI execution (run_task)
  • relevance.py -- Embedding-based relevance scoring + compression via Ollama
  • eval_runner.py -- Evaluation framework: runs benchmark under 4 context format conditions
  • eval_compare.py -- Eval compare: Bearing (8 sessions) vs single session (1 mega-prompt)
  • agent.py -- Tool-use agent via provider adapters (OpenAI Responses or Anthropic Messages, urllib/no SDK), with prompt caching + reasoning effort
  • compressor.py -- Mid-conversation history compression (API or Ollama backends)
  • retriever.py -- Embedding-based selective history retrieval via Ollama (nomic-embed-text)
  • eval_agent.py -- Eval: agent with/without compression/caching/retrieval vs Codex -p (7 conditions)
  • test_sanity.py -- Quick sanity test for caching + reasoning features
  • tasks_schema.py -- Dataclasses for Task, TaskQueue, TaskResult
  • status_writer.py -- Generates status.md from task queue state

Eval Framework

Four context format conditions: prose, structured, embedding, embedding+llm.

Eval Compare (bearing eval-compare)

Compares Bearing's 8-session approach against a single mega-prompt session. This tests the core value proposition: task isolation prevents context accumulation and compaction. The single session gets the same task prompts and FOCUS directives but must build everything in one accumulated context. Key metrics: total tokens, compaction count, per-task quality.

Key Learnings

Embedding similarity baseline is high for same-domain text. nomic-embed-text cosine similarity for chunks within the same project bottoms out around 0.5-0.6, not 0.2-0.3. Default thresholds are set at keep=0.75, drop=0.55 to account for this. Benchmarks that need chunks to actually drop require genuinely unrelated domains (e.g., different languages or problem spaces), not just "parallel feature tracks" in the same codebase.

Read the full file on GitHub · 117 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. 2d ago First seen · 117 lines · 1,438 tokens per session scan A 60827cc69883

Subscribe to this mod's changes

bearing AGENTS.md is an instructions file published in the GitHub repository rocketvish/bearing (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,438 tokens to every session, about $0.0072 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.