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 skills add erda-project/skills --skill erda-issuegit clone --depth 1 https://github.com/erda-project/skillsWrote 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/erda-project/skills/erda-issue)<a href="https://agentmods.dev/skills/erda-project/skills/erda-issue"><img src="https://agentmods.dev/badge/skills/erda-project/skills/erda-issue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/erda-project/skills/erda-issue"><img src="https://agentmods.dev/badge/skills/erda-project/skills/erda-issue.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00071 | $0.00928 |
| Opus 5.5 | $0.00028 | $0.00371 |
| Sonnet 5.5 | $0.00014 | $0.00186 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
erda-issue 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ERDA Issue
This skill is built around the real erda-cli issue command surface and keeps state-changing actions behind explicit user confirmation.
It supports:
create: schema-driven issue creation (user confirms beforeerda-cli issue create)next: propose the next state based onerda-cli issue schema(plan-only; no update)update: set an explicit target state (user confirms beforeerda-cli issue update)bind: parent/child issue binding (inclusionvsconnection), also behind confirmation
Keywords
This skill explicitly covers these command surfaces and intents (useful for automatic skill matching):
erda-cli issue createerda-cli issue schemaerda-cli issue listerda-cli issue updateerda-cli issue bindissue state transitionscreate bug/create task/create requirementnext(plan-only proposal) /update(explicit target)inclusion/connectionbinding
Use This Skill For
- creating ERDA issues (bug / task / requirement)
- run
erda-cli issue create(after confirmation) - guiding issue state transitions using
erda-cli issue schema - when the user says “go to the next step”, proposing the next target state and asking for confirmation
- run
erda-cli issue update(by explicit--stateor--state-id, after confirmation) - binding tasks to requirements (default relation:
inclusion) - binding issues as an association (relation:
connection) when the user explicitly requests “关联/associated” - run
erda-cli issue bindfor parent/child relations (after confirmation)
Safety Gates (Hard Rules)
- No state-changing apply without confirmation
erda-cli issue createonly after the user explicitly confirms.erda-cli issue updateonly after the user explicitly confirms.erda-cli issue bindonly after the user explicitly confirms.
nextis plan-onlynextmust not callerda-cli issue update.nextalways asks the user whether to apply.
- Stop condition: no wrap-around
- If the current state is already the last state in the schema-defined transitions/ordering,
nextmust error and instruct the user to use explicitupdate --state/--state-id.
- If the current state is already the last state in the schema-defined transitions/ordering,
What ships with it
3 files 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.
- 2mo ago First seen · 80 lines · 71 tokens per session scan A dc108a562357
erda-issue is a skill published in the GitHub repository erda-project/skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 928 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.