arcgentic
Skill286 starsChanged 5 months agoMITView on GitHub
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
In this repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agency-rosterSkill
- audit-roundSkill
- claude-code-session-brokerSkill
- close-roundSkill
- codex-thread-orchestrationSkill
- codify-lessonSkill
- cross-session-handoffSkill
- execute-roundSkill
- orchestrate-roundSkill
- plan-roundSkill
- pre-round-scanSkill
- session-modeSkill
- source-intakeSkill
- spec-governanceSkill
- track-refsSkill
- using-arcgenticSkill
- verify-gatesSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
32 rules. About 0 are common, 15 are distinctive, and 17 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈15
Distinctive · estimate
This author's own choices. Worth a look.
17
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use this before build-feature, executing-plans, or direct coding whenever the user asks to use Arcgentic.
- Very specific: line 13
Do not directly implement, test, or scaffold the requested feature from the Orchestrator, even in a greenfield or empty project.
- Very specific: line 19
Treat the current thread as Orchestrator and rename the current Codex thread to exactly Orchestrator before dispatching any role.
- Distinctive: line 22
If yes, continue with project-scoped orchestration.
- Distinctive: line 23
If no, stop and ask the user to open or create a saved project workspace.
- Very specific: line 24
If this is the first Arcgentic V2 run in the project and no mode is already stored, judge the user's idea before dispatching Planner:
- Distinctive: line 34
Ask the user to confirm the recommendation or override it.
- Distinctive: line 35
Do not dispatch Planner until the user has chosen one project-level mode.
- Distinctive: line 44
Use the chosen mode for the whole project.
- Distinctive: line 48
Do not create projectless Planner / Developer / Test / Auditor threads.
- Distinctive: line 49
Use the strongest available Codex model for real Planner / Developer / Test / Auditor work.
- Distinctive: line 50
Test / Auditor work. Do not default role threads to a lightweight or spark model unless the user explicitly asks for a low-cost smoke test.
- Very specific: line 59
Before reading implementation files, running tests, checking git log, or summarizing prior work, initialize/check …
- Very specific: line 63
If state exists and current_round.state is closed, treat the new user request as input for Planner only when it asks for new work.
- Very specific: line 67
Run v2-session-plan with the user-selected mode on first use, or without --mode after the mode is already stored:
- Very specific: line 78
If the plan is active and contains an action, dispatch that one role before any verification or implementation inspection, then call …
- Very specific: line 83
If state is closed and the plan has no actions, stop: the round is terminal at the project level, all role threads are idle, and …
- Distinctive: line 105
After init, update the state for V2 Codex mode:
- Very specific: line 124
If arcgentic CLI is not available, report installation failure instead of pretending Arcgentic is active.
- Distinctive: line 126
If the current thread is projectless or cannot create project-scoped role threads, stop.
- Very specific: line 128
If .agentic-rounds/state.yaml records delegation source_thread_id as the Orchestrator session by mistake, do not create Planner.
- Very specific: line 142
If .agentic-rounds/state.yaml cannot be created or validated, stop.
- Distinctive: line 143
If role threads cannot be created in the current project/workspace, stop.
- Very specific: line 144
If a role thread is slow, send at most one status/constraint-tightening message.
- Very specific: line 147
After dispatching a role prompt, call arcgentic v2-dispatch-role and end the Orchestrator turn.
- Very specific: line 150
If arcgentic v2-return-signal rejects the role output, stop and report the rejected signal.
- Very specific: line 152
Do not silently fall back to "Arcgentic-style" hand-written evidence.
- Distinctive: line 153
Do not treat "greenfield" or "empty repo" as permission for Orchestrator implementation.
- Distinctive: line 155
Do not verify, summarize, or inspect a previous closed round as the response to a new implementation request.
- Very specific: line 157
Do not auto-dispatch Planner from project-level closed unless there is a new user request.
- Distinctive: line 161
Do not run ordinary coding work before Planner has produced or approved the round plan.
- Distinctive: line 189
Do not create source files, tests, handoff docs, self-audits, user-test reports, or external audit verdicts from the Orchestrator.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Arcgentic
This is the Codex-facing entry skill for Arcgentic V2.
Use this before build-feature, executing-plans, or direct coding whenever
the user asks to use Arcgentic.
Do not directly implement, test, or scaffold the requested feature from the Orchestrator, even in a greenfield or empty project. Arcgentic work starts by dispatching Planner.
Immediate behavior in Codex
- Treat the current thread as
Orchestratorand rename the current Codex thread to exactlyOrchestratorbefore dispatching any role. - Determine whether the current thread has a real project/workspace root.
- If yes, continue with project-scoped orchestration.
- If no, stop and ask the user to open or create a saved project workspace.
- If this is the first Arcgentic V2 run in the project and no mode is already
stored, judge the user's idea before dispatching Planner:
Run:
arcgentic session-mode recommend-v2 --idea '<current user request>'- Present the recommended mode, confidence, reasons, and tradeoff in natural language.
- Ask the user to confirm the recommendation or override it.
- Do not dispatch Planner until the user has chosen one project-level mode.
- The two V2 modes are:
single-session-subagent: faster and usually finishes sooner. Planner, Developer, Test, and Auditor run as named subagents inside the current Orchestrator session, so audit isolation is weaker. The first use of a role creates that fixed named role identity; later rounds reuse it.multi-session-subthread: slower. Planner, Developer, Test, and Auditor run in fixed project threads, so role separation and external-audit evidence are stronger.
- Use the chosen mode for the whole project. Do not ask again per round unless the user explicitly starts a new project or requests a reset.
- In
multi-session-subthread, use the current project/workspace as the only valid target for role threads after initialization. - Do not create projectless Planner / Developer / Test / Auditor threads.
- Use the strongest available Codex model for real Planner / Developer / Test / Auditor work. Do not default role threads to a lightweight or spark model unless the user explicitly asks for a low-cost smoke test.
- Record the current thread as fixed role
Orchestratorin.agentic-rounds/state.yamlbefore dispatching Planner. If the host cannot provide the current Orchestrator thread id, stop because push-return cannot work. In Codex delegation-created threads, do not treat the delegationsource_thread_idas the current Orchestrator id. It identifies the upstream supervising thread, not the project-scoped Orchestrator. - Before reading implementation files, running tests, checking git log, or
summarizing prior work, initialize/check
.agentic-rounds/state.yamland runv2-session-plan. - Initialize
.agentic-rounds/state.yamlif it does not exist. If state exists andcurrent_round.stateisclosed, treat the new user request as input for Planner only when it asks for new work. Status, inspection, review, or "is this complete?" requests are terminal idle and must not rewriteactive_user_requestor dispatch Planner. - Run
v2-session-planwith the user-selected mode on first use, or without--modeafter the mode is already stored:
arcgentic v2-session-plan \
--state .agentic-rounds/state.yaml \
--host codex \
--user-request '<current user request>' \
--mode <single-session-subagent|multi-session-subthread>- If the plan is active and contains an action, dispatch that one role before
any verification or implementation inspection, then call
arcgentic v2-dispatch-roleand end the Orchestrator turn inmulti-session-subthread, or create/reuse the named role agent directly insingle-session-subagent. If state isclosedand the plan has no actions, stop: the round is terminal at the project level, all role threads are idle, and Orchestrator should wait for a new user request. - Load
codex-thread-orchestrationand follow it.
Bootstrap if state is missing
Find the plugin root:
PLUGIN_ROOT="${ARCGENTIC_PLUGIN_ROOT:-$HOME/plugins/arcgentic}"Then initialize state:
bash "$PLUGIN_ROOT/scripts/state/init.sh" \
--project-root . \
--project-name "$(basename "$PWD")" \
--round-naming "R<n>"After init, update the state for V2 Codex mode:
python - <<'PY'
from pathlib import Path
import yaml
path = Path(".agentic-rounds/state.yaml")
state = yaml.safe_load(path.read_text(encoding="utf-8"))
state.setdefault("project", {})["arcgentic_v2"] = {
"host": "codex",
"role_sessions": {},
}
path.write_text(yaml.safe_dump(state, sort_keys=False), encoding="utf-8")
PYFail-closed rules
- If
arcgenticCLI is not available, report installation failure instead of pretending Arcgentic is active. - If the current thread is projectless or cannot create project-scoped role threads, stop.
If
.agentic-rounds/state.yamlrecords delegationsource_thread_idas the Orchestrator session by mistake, do not create Planner. Repair only that field with:arcgentic v2-record-session \ --state .agentic-rounds/state.yaml \ --host codex \ --role orchestrator \ --thread-id <current-orchestrator-thread-id> \ --title Orchestrator \ --repair-current-orchestrator- If
.agentic-rounds/state.yamlcannot be created or validated, stop. - If role threads cannot be created in the current project/workspace, stop.
- If a role thread is slow, send at most one status/constraint-tightening
message. If it still does not return a valid
RoleReturnSignal, stop with a role-timeout status. Do not continue the workflow in the Orchestrator. - After dispatching a role prompt, call
arcgentic v2-dispatch-roleand end the Orchestrator turn. The Orchestrator resumes only when the pending role actively sends return information back to the Orchestrator thread. - If
arcgentic v2-return-signalrejects the role output, stop and report the rejected signal. Do not repair it by hand in the Orchestrator. - Do not silently fall back to "Arcgentic-style" hand-written evidence.
- Do not treat "greenfield" or "empty repo" as permission for Orchestrator implementation.
- Do not verify, summarize, or inspect a previous closed round as the response to a new implementation request. Route the request to Planner first.
- Do not auto-dispatch Planner from project-level
closedunless there is a new user request. Closed without a new request means the project workflow is stopped. Round-level PASS is not closed; it must advance through the stored project plan. - Do not run ordinary coding work before Planner has produced or approved the round plan.
- Planner, Developer, Test, and Auditor must not mutate
.agentic-rounds/state.yaml, run transition commands, dispatch roles, consumeRoleReturnSignal, or close rounds. They write their role-owned artifacts and return natural-language output plus onearcgentic-role-returnfooter for the Orchestrator to consume. - Role threads must not stop after acknowledging their role. They must complete
role-owned work in the same turn, using tools as needed, before returning
RoleReturnSignal. Developer, Test, and Auditor consume prior-role artifacts fromproject.arcgentic_v2.last_signal.artifacts. - Role threads must actively wake the Orchestrator by sending their completed natural-language output and machine footer to the recorded Orchestrator thread. The Orchestrator must not poll role threads to discover completion.
- Planner must do discovery before handoff: search GitHub or equivalent public references for reliable comparable projects, scan local skills/plugins/MCP servers/connectors/tools, then write the selected references and tools into a detailed Markdown handoff. Each downstream role must read the handoff artifact named in the Orchestrator prompt before acting.
- Planner project-close returns must write a closeout artifact, create a local
closeout commit, include
artifacts.closeoutandartifacts.commit, and usenext_recommended_role: null. Closed projects are terminal idle unless the user provides a genuinely new work request. - Auditor PASS fact rows must use lifecycle-stable evidence: committed
artifacts, fixed git hashes, artifact file contents, state history, and
test/build output. Do not use mutable live routing fields such as
current_round.state,project.arcgentic_v2.last_signal.role, orproject.arcgentic_v2.last_signal.stateas PASS facts unless the command reads an immutable committed snapshot. - Do not create source files, tests, handoff docs, self-audits, user-test reports, or external audit verdicts from the Orchestrator. Those belong to Planner, Developer, Test, and Auditor role threads.
Continue
Load and follow:
codex-thread-orchestrationfor Codex V2 fixed-role threads.using-arcgenticfor the general round-state vocabulary and state-machine rules.
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.

