add-agent
Skill71 starsChanged 36 days agoMITView on GitHub
Add a new agent or LLM seat to the graph. Covers the prompt file, seat registry, node factory, graph wiring, ticker-isolated memory, and the tests that must accompany it.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- venkateshv1266/pi-harnesstheir own version, first seen Nov 1, 2026
- chacosoldier/compabobtheir own version, first seen Oct 23, 2026
- axrmxv/claude-configtheir own version, first seen Oct 13, 2026
- FISHers6/clawBrotheir own version, first seen Oct 8, 2026
- mattolson/agent-sandboxtheir own version, first seen Oct 8, 2026
- microsoft/Sicotheir own version, first seen Jun 11, 2026
Used with
Projects with it also use setup.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 3 projects that use this
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- microsoft/Sico★ 253same name
- mattolson/agent-sandbox★ 212same name
- BerriAI/litellm-skills★ 84same name
- chacosoldier/compabob★ 34same name
- FISHers6/clawBro★ 28same name
- venkateshv1266/pi-harness★ 2same name
- axrmxv/claude-config★ 1same name
- theopengroup/rune-harness★ 1same name
- tjg37/ironclaw★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- add-agentSkill
- analyze-tickerSkill
- diagnose-runSkill
- maintain-agent-metadataSkill
- run-pipelineSkill
- run-testsSkill
- analyze-tickerSkill
- diagnose-runSkill
- run-testsSkill
- validation-batchSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Create prompts/<agent_key>.json with agent_key, agent_name, version, category, requires_tools, system_message, and a metadata block …
- Very specific: line 25
Add a SeatId and SeatSpec in src/llm_runtime/seats.py.
- Very specific: line 49
Add the factory in the owning module under src/agents/, following the sibling patterns.
- Distinctive: line 53
If the node runs in parallel with others, three things are mandatory: give it its own state field rather than sharing one under a …
- Distinctive: line 72
If the agent needs memory, add its instance through the ticker-isolated factory so it gets its own per-ticker collection.
- Very specific: line 78
Add tests/agents/test_<agent>.py, and extend the legacy-parity test if the seat has a legacy construction path.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Adding an agent
Six steps, in order. Each one is load-bearing; skipping the seat registry in particular produces an agent that constructs but is never dispatched, and that failure is silent.
1. Prompt
Create prompts/<agent_key>.json with agent_key, agent_name, version,
category, requires_tools, system_message, and a metadata block carrying
last_updated and a changes line. Edit it only through Python's json module —
the prompt-contract rule loads automatically when you touch that directory.
2. Seat
Add a SeatId and SeatSpec in src/llm_runtime/seats.py. Three keys must line up
with name spaces that already exist; do not invent a second one:
prompt_keymatches the JSON filenamebudget_keymatches anAGENT_OUTPUT_BUDGET_FRACTIONSentrycallback_namematches the token-tracking display name
Choose the binding group deliberately. A verification seat belongs in review,
where vendor diversity is the point; an analysis input belongs in base. Declare
requires honestly — capability validation is what catches a chat-only model bound to
a tool-calling seat, before the run rather than during it.
Per-seat call semantics — temperature, client timeout, tier pins — are
SeatExecutionPolicy data, never an if seat == ... at a call site. Putting a pin at
the call site means only that caller gets it.
Choose the seat's TimeoutClass from src/llm_runtime/timeouts.py. The runtime owns
total application attempts; transports configure one SDK attempt per dispatch. Do not
add a per-seat retry setting or a construction-time flex deadline.
Google's aiohttp connection recovery may resend internally; verify effective sends
and application retry/rate-limit branch counts rather than model fields alone.
3. Node factory
Add the factory in the owning module under src/agents/, following the sibling
patterns. Construct the model with build_model_for_seat(SeatId.NEW_AGENT, ...) —
never a provider constructor directly. An architecture test enforces that boundary.
If the node runs in parallel with others, three things are mandatory: give it its own state field rather than sharing one under a last-write-wins reducer, tag its outgoing messages with the agent key, and filter incoming messages to its own history. Remember the retry path — tagging applied only to the main response is a recurring bug here.
Bound every artifact write with cap_state_value, and every blocking call with the
repository's hard-timeout wrapper.
4. Graph
Register the node in src/graph/ with its routing and tool-node wiring. Every gate
that decides whether a seat runs must read the binding plan, not a legacy credential.
A gate keyed on a provider key that a newer configuration legitimately does not set
will wire the node and never dispatch to it, raising nothing; the only evidence is a
NOT_RUN status in the saved artifact.
5. Memory
If the agent needs memory, add its instance through the ticker-isolated factory so it gets its own per-ticker collection. Never reach for a global memory object — that is what lets one company's data contaminate another's analysis.
6. Tests
Add tests/agents/test_<agent>.py, and extend the legacy-parity test if the seat has
a legacy construction path. Cover the edge cases this system actually hits: missing
data, a refused or empty provider response, malformed output, and the timeout path.
Then run the owning directory, make test-prompts, and poetry run ruff check src/.
Full history: docs/AGENT_ROSTER.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

