Open SWE is an open-source software factory that gives coding tasks to an asynchronous agent, which investigates repositories, changes code, validates the results, and delivers pull requests. Engineering teams use it to automate code changes, reviews, CI follow-up, and related repository work from dashboards and connected tools.
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 skills/langchain-ai/open-swe/continual-learningnpx skills add langchain-ai/open-swe --skill continual-learninggit clone --depth 1 https://github.com/langchain-ai/open-sweWrote 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/skills/langchain-ai/open-swe/continual-learning)<a href="https://agentmods.dev/skills/langchain-ai/open-swe/continual-learning"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/continual-learning.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 5.1 | $0.00089 | $0.00535 |
| Opus 5 | $0.00044 | $0.00267 |
| Sonnet 5 | $0.00018 | $0.00107 |
| Haiku 4.5 | $0.00009 | $0.00053 |
Grade A, and why
continual-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 6d 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
Continual learning
You are refining the existing review-style prompt for the repository named in the system prompt, using outcomes the reviewer has accrued since the last run. The goal is to raise recall (catch more real bugs) without hurting precision (stop repeating dismissed ones).
1. Read outcomes first
Call read_finding_outcomes once. It returns this repo's past findings split into:
confirmed— resolved by a follow-up commit or 👍'd. These are real bug patterns this team fixes. Promote the recurring ones into the prompt's "hunt for" guidance, quoting thefile/diff_hunkcontext so the rule stays concrete.dismissed— dismissed or 👎'd. These are false-positive patterns. Add the recurring ones to the prompt's "do not flag" section so the reviewer stops repeating them.
Look for repetition, not one-offs. A single dismissed finding is noise; the same class dismissed several times is a rule.
2. Reconcile against the current prompt
The current custom_prompt is the starting point — you are editing it, not rewriting
from scratch. Read it (it is summarized for you / available via the dashboard record).
Keep what still holds, strengthen rules the outcomes confirm, and remove or soften rules
the outcomes contradict. Optionally do a light gh top-up to confirm a pattern,
but outcomes are the primary signal — do not re-run a full PR crawl.
Stay aligned with the reviewer-agent themes in the system prompt.
3. Save
Call save_review_style_prompt once with the refined custom_prompt (400–1200 words),
an analysis_summary that names what changed this cycle (e.g. "promoted N-pattern after
3 confirmed fixes; dropped M-pattern after repeated dismissals"), and the
top_reviewers / counts you have. If outcomes were empty and nothing changed, say so in
analysis_summary and re-save the existing prompt unchanged rather than degrading it.
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.
- 6d ago First seen · 44 lines · 89 tokens per session scan A 6197ca396af5
continual-learning is a skill published in the GitHub repository langchain-ai/open-swe (10,666 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 535 once invoked, about $0.0004 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 skills, from other repositories
langbot-eba-adapter-dev
Build, refactor, and test LangBot platform adapters for the Event-Based Agents architecture. Use when adding or migrating Telegram, Discord, or other messaging platform adapters to the EBA adapter layout, validating unified event/message conversion, writing live adapter probes, or using standalone plugin runtime plus…
langbot-plugin-dev
Develop, debug, and test LangBot plugins. Use when creating new LangBot plugins, fixing plugin bugs, setting up a LangBot test environment, or testing plugins via WebSocket. Covers plugin component architecture (EventListener, Command, Tool), the plugin SDK API (invokellm, getllmmodels, sendmessage, plugin storage)…
langbot-mcp-ops
Operate a LangBot instance through its built-in MCP (Model Context Protocol) server. Use when an AI agent needs to manage LangBot — list/create/update/delete bots, pipelines, models, knowledge bases, MCP servers, and skills — over MCP instead of raw HTTP. Covers the /mcp endpoint, API-key auth (web-UI lbk keys and the…
langbot-space-ops
Browse and search the LangBot Space marketplaces (plugins, MCP servers, skills) through the Space MCP server. Use when an AI agent needs to discover LangBot extensions on space.langbot.app over MCP. Covers the /mcp endpoint, Personal Access Token (PAT) auth, the tool surface, and client configuration. Triggers on…
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.
langbot-env-setup
Prepare a local LangBot development and testing environment for an AI agent. Use when setting up WSL or Linux development, shared local URL variables, proxy variables, backend/frontend startup, Playwright MCP browser access, GitHub OAuth browser login, persisted Chrome profiles, or future Codex computer-use…