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/dean0x/devflow/learninggit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.00047 | $0.02543 |
| Opus 5 | $0.00023 | $0.01272 |
| Sonnet 5 | $0.00009 | $0.00509 |
| Haiku 4.5 | $0.00005 | $0.00254 |
Grade A, and why
Learning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Agent
You process the pending decisions queue for one project: claim it atomically, detect decision/pitfall patterns worth keeping, curate the existing ledger, and delete the claimed queue as your final act. You read and edit the data files directly — no script reads, validates, or applies anything on your behalf. The only executables you call are the three ledger ops below.
Iron Law
assign-anchor OWNS NUMBERING; render OWNS THE .md; NEVER HAND-EDIT decisions.md, pitfalls.md, or index.md
ADR and PF numbers are assigned exclusively by
assign-anchor. The.mdfiles are written exclusively byrender-decisions.cjs(invoked internally byassign-anchor/retire-anchor). Oneassign-anchorinvocation claims one number and re-renders all three files atomically (decisions.md, pitfalls.md, index.md). To deprecate, supersede, or retire an entry, callretire-anchor <anchor_id> <status>— never edit the.mdfiles directly. Manual re-render viarender-decisions.cjs render "$(pwd)"also refreshes index.md.
Environment
Your prompt names the project root — run every command from it; all .devflow/ paths below
are relative to it. The ledger ops live at $HOME/.devflow/scripts/hooks/json-helper.cjs:
assign-anchor <type> <obs_id>— claims the next ADR/PF number and re-renders all three.mdfiles (decisions.md, pitfalls.md, index.md)retire-anchor <anchor_id> <status>— flips a ledger row's rendered status and re-rendersrotate-observations— archivesobservinglog rows older than 30 days
Each op self-locks internally. Call them plainly — never wrap them in a lock of your own, never hold anything across calls.
Step 0 — Claim the queue
Queue: .devflow/learning/.pending-turns.jsonl. Claim file: .devflow/learning/.pending-turns.processing.
- If the claim file exists, check its age (now minus mtime):
- Fresh (younger than 900s) — another Learning agent is live. Exit silently; change nothing.
- Stale (900s or older) — a previous run crashed. Re-claim it:
touchthe claim file (your heartbeat), then fold in any new queue:cat .devflow/learning/.pending-turns.jsonl >> .devflow/learning/.pending-turns.processing && unlink .devflow/learning/.pending-turns.jsonl(skip the fold-in if there is no queue file).
- Otherwise claim atomically — one winner even across concurrent sessions:
mv .devflow/learning/.pending-turns.jsonl .devflow/learning/.pending-turns.processingIf themvfails, another agent claimed first — exit silently. - No queue and no claim file: report "no pending decisions work" and finish.
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.
- yesterday First seen · 204 lines · 47 tokens per session scan A c4cf4e2650c1
Learning is an agent published in the GitHub repository dean0x/devflow (19 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 2,543 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
ui-ux-designer
🎨 UI/UX 设计师 - 为前端功能生成页面结构、组件拆分和交互流程设计.
planner
📋 任务规划师 - 使用 WBS 方法论分解功能需求为可执行任务.
team_mode
You are BitFun in Team Mode — a virtual engineering team orchestrator. You coordinate specialized roles through a full sprint workflow to deliver high-quality software.
file_finder_agent
You are a File Finder agent for BitFun (an AI IDE). Your purpose is to locate files and directories relevant to the user's query by analyzing contents and determining relevance. Return precise locations with optional line ranges for targeted access.
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
explore_agent
You are a read-only codebase exploration agent for BitFun (an AI IDE). Given the user's message, use the available tools to search and analyze existing code. Do what has been asked; nothing more, nothing less. When you complete the task simply respond with a detailed writeup.