forge-agent
/forge-agent
Brief, build, and prove a new agent (Claude Code subagent/skill, Cursor agent, Agent SDK, Python/LangGraph, scheduled job) before it ships. Use when the user types /forge-agent, says "create/build/design/spec/scaffold an agent", "brief an agent", "ask me the agent questions", or gives a one-liner naming a stack ("SDK + SQLite to do X") but no outcome or eval.
- Author
- mjha-arya ↗
- Repository
- claude-code-skills ↗
- Licence
- MIT
- Last repository change
- 10.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 1
No signals detected. Repository changed on 10.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Brief, build, and prove a new agent (Claude Code subagent/skill, Cursor agent, Agent SDK, Python/LangGraph, scheduled job) before it ships. Use when the user types /forge-agent, says "create/build/design/spec/scaffold an agent", "brief an agent", "ask me the agent questions", or gives a one-liner naming a stack ("SDK + SQLite to do X") but no outcome or eval.
Triggers from the description
Arguments
/forge-agent One-line idea of the agent, however rough
Original author description
Brief, build, and prove a new agent (Claude Code subagent/skill, Cursor agent, Agent SDK, Python/LangGraph, scheduled job) before it ships. Use when the user types /forge-agent, says "create/build/design/spec/scaffold an agent", "brief an agent", "ask me the agent questions", or gives a one-liner naming a stack ("SDK + SQLite to do X") but no outcome or eval.
How it works
- Gate 1: Brief (no build without it)
- Gate 2: Build
- Gate 3: Prove
- Close
SKILL.md preview
---
name: forge-agent
description: Brief, build, and prove a new agent (Claude Code subagent/skill, Cursor agent, Agent SDK, Python/LangGraph, scheduled job) before it ships. Use when the user types /forge-agent, says "create/build/design/spec/scaffold an agent", "brief an agent", "ask me the agent questions", or gives a one-liner naming a stack ("SDK + SQLite to do X") but no outcome or eval.
argument-hint: "One-line idea of the agent, however rough"
---
Works well by voice: ask **at most 4 numbered questions per round**, each with a **default**, so
replies like "default" or "1 default, 2 is …" work. One round per message, then wait. Pre-fill whatever
the ask already answers and mark it "taken". If a name or number looks odd (dictation garbles them),
ask ONE question and never guess. Outcome before stack: park any named tech ("Noted SQLite, deciding
at step 3"). Choose the model only after the golden cases exist.
**Config:** `AGENTS_ROOT` is where your agents live (default: `./agents`). `CONSTITUTION` is your rules
file (default: [Constitution of Agents](https://github.com/mjha-arya/constitution-of-agents) `AGENTS.md`)
and `GLOSSARY` is its agent registry.
## Gate 1: Brief (no build without it)
1. **Reuse:** read `GLOSSARY`. If an agent already covers the job, propose extending it instead.
Report in one line how many agents are still `Authored, not verified` (grep `**Status:**` in
`AGENTS_ROOT/**/README.md`).
2. **Job** (outcome, not stack) · **Done when** (a number; *default: at least 4/5 golden pass, zero
safety violations*) · **5 golden cases**, each input → ideal output, at least 1 edge case and at least
1 adversarial (*default: you draft, the user corrects*).
3. **Data** in → out, with exact paths · what goes stale (*default: re-fetch each run, cache at most 24 h*) ·
**persist?** If nothing needs to persist, no DB (*default: stdlib `sqlite3`*) · memory write-back.
Procedural changes go to `PROPOSALS.md` for the user's yes.
4. **Tools:** read set, write = exact paths only, and outward actions (post/email/schedule/deploy) need
the user's yes · PII/secret check on output · who owns it when it breaks (*default: the user, via
their notification channel*).
5. **Runtime + REAL auth:** `claude -p` | subagent/skill | Agent SDK | LangGraph. **Test the auth now.**
Placeholder keys are the most common reason an agent never runs. Single agent or a pattern ·
`max_turns` · $/run (*default: `claude -p` or subagent, single, 30 turns, $1*).
6. **Failure → behaviour:** login wall, empty data, rate limit, tool error, low confidence
(*default: retry at most 3 times, exit 2, send a notification, JSONL trace in `data/runs/`*).
→ Write `AGENTS_ROOT/<Name>/BRIEF.md` + `evals/golden.jsonl`. Read it back in 10 lines or fewer and get
the user's yes. No golden cases → mark it `DRAFT: no eval` and stop.
## Gate 2: Build
7. Read `CONSTITUTION` in full and pick the runtime by its rules (one line).
8. The soul **embeds** the applicable rules (standalone, no links): purpose, inputs, hard rules, a
`needs_human` list, and an exact return format ending in NOT CHECKED.
9. Build it yourself, or hand large builds to another coding agent with the brief path + spec, then
review the diff.
## Gate 3: Prove
10. Run **every** golden case on the real model/runtime. Log each to `data/runs/*.jsonl`.
11. Score: deterministic checks + tool-call count (no loops, no duplicate calls) + an LLM judge only
for the fuzzy part.
12. Fail → fix the soul → commit `"failure fixed → expected change"` → rerun. At most 3 loops, then
report the blocker honestly.
13. Pass bar met → README `**Status:** Verified (<date>, <score>)`. Otherwise `Authored, not verified`.
Never claim a run that didn't happen.
## Close
14. Add or update the agent's row in `GLOSSARY` and commit it.
15. Reply in one line: path · score · NOT CHECKED.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · mjha-arya/claude-code-skills | 100 | MIT |
| aaddrick/ticketmill | 100 | MIT |
Database snapshot: 13.11.2026 · package version 22af0e7a3830 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100forge-install
This skill should be used when the user wants to "install the Forge plugin", "set up Forge", "install forge-agent-lens-for-claude-code", "configure Forge for the first time", "get started with Forge tracing", or needs to complete the initial setup of the Forge Agent Lens for… - 100create-agent
Use when the user wants to create a new agent teammate, scaffold a scheduled Claude persona, or asks to "create an agent", "new agent", "add an agent", "add a job", "scheduled task", "scaffold an agent", "build an agent", "make an agent", or "/claudeclaw:create-agent". Trigger… - 95skill-forge
Use when creating new Rune skills, editing existing skills, or verifying skill quality before deployment. Applies TDD discipline to skill authoring — test before write, verify before ship. - 100tool-forge
自适应工具铸造:探测 TOOL_GAP 后为当前 Agent 铸造工具与技能骨架并登记能力目录。触发词:缺工具、TOOL_GAP、造一个工具、自适应构建、forge、工具铸造、补技能。 - 100forge-config
This skill should be used when the user wants to "configure Forge", "set Forge project", "change Forge project", "set wandb api key", "update Forge settings", "show Forge config", "change Forge configuration", "restart the Forge daemon", "apply Forge config changes", "restart… - 100agent-forge
Build, configure, or repair task agents and agent apps, including durable, tool-calling, multi-agent, and scheduled apps. Create bounded playbooks and toolboxes, or perform a read-only review of a specified code change. Use for explicit agent-building, agent automation,…