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/langbot-app/langbot/langbot-skills-maintenancenpx skills add langbot-app/LangBot --skill langbot-skills-maintenancegit clone --depth 1 https://github.com/langbot-app/LangBotWhat 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 | $0.00049 | $0.00539 |
| Opus 5 | $0.00024 | $0.00269 |
| Sonnet 5 | $0.00010 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
langbot-skills-maintenance 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LangBot Skills Maintenance
Use this skill before changing reusable assets in this repository.
Workflow
- Read
AGENTS.md,skills/.env, and the relevant existing skill files. - Classify the change:
SKILL.mdfor routing and concise operating rules.references/*.mdfor canonical detailed workflows.cases/*.yamlfor executable test-plan skeletons.suites/*.yamlfor reusable groups of case ids.fixtures/fixtures.jsonfor deterministic fixture readiness metadata.reports/evidence/<run-id>/automation-result.jsonas automation output andreports/evidence/<run-id>/result.jsonas final judgment output; neither is a catalog asset to commit.troubleshooting/*.yamlfor one reusable failure mode.
- Search existing assets before adding new files:
rg "<feature|error|case id>" skillsbin/lbs case listbin/lbs suite listbin/lbs fixture list
- Put detail in one canonical place and link to it from cases or routing bullets.
- Run the checks in
AGENTS.mdafter edits.
Entropy Rules
- Prefer extending an existing reference or troubleshooting entry when the root cause is the same.
- Keep cases short: setup, action, evidence, pass/fail checks. Do not paste long prompts or debug transcripts when a reference exists.
- Put machine-checkable inputs in
env,automation_env, or fixtures; put operator-confirmed assumptions inpreconditionssotest plancan surfacemanual_check. - Keep suites short: title, intent, tags, and ordered case ids. Do not duplicate case steps inside a suite.
- Keep fixture manifests factual: id, title, path, kind, and related case ids. Do not encode environment-specific absolute paths.
- Keep troubleshooting entries narrow: symptoms, patterns, likely causes, fixes, related assets.
- Do not hardcode local ports, browser profile paths, secrets, tokens, or provider keys.
- Use
bin/lbs index --checkto verify the committed index is current without writing it; runbin/lbs indexwhen the index needs regeneration.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 41 lines · 49 tokens per session scan A ffcef2dfec7b
langbot-skills-maintenance is a skill published in the GitHub repository langbot-app/LangBot (17,616 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 539 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 skills, from other repositories
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
bootstrap-repo-analysis
First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
gzh_article
公众号图文创作 / 推文 / 官方号文章 (official account article) — 端到端：选题→搜集→成文→配图→去AI化→公众号内联样式排版→交付/草稿箱。honors user persona & style memory.
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.