القائمة
Bootstrap loader for the DG-Anvil plugin. Enumerates the five primitives, seven skills, five commands, and the core loop. Loaded at session-start.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
On verify or judge fail, append a non-null lesson to the Ledger and re-queue the task. Null lessons are refused; the task escalates instead.
Dispatch one fresh subagent per plan task inside a per-task git worktree. Capture diff and tool output; never carry state across dispatches.
Author a machine-readable contract before execution. Produces anvil/contract.yml with four verification-level slots per criterion and Ledger-sourced counter-examples.
Decompose a confirmed contract into an atomic task DAG with wave ordering. Every task cites one or more contract criterion ids.
Meta-skill governing every change to any skill file. Requires a RED-then-GREEN subagent pressure transcript before a skill change is accepted.
Dispatch the Court on evidence-only inputs (contract + diff + verify output + confidence). The Court is not a persona; it is a structured adjudicator.
استنادا إلى تصنيف SOC المهني
| name | using-anvil |
| description | Bootstrap loader for the DG-Anvil plugin. Enumerates the five primitives, seven skills, five commands, and the core loop. Loaded at session-start. |
DG-Anvil enforces the Anvil loop as structural gates, not advisory prompts.
Five primitives: Contract, Plan, Loop, Ledger, Court.
Seven skills that compose the loop:
contracting - turn an intent into a machine-readable contract with four verification levels per criterion.planning - decompose the contract into an atomic task DAG with wave ordering; every task cites contract criterion ids.executing - dispatch a task to a fresh subagent in an isolated worktree.verifying - run the four verification probes (Exists, Substantive, Wired, Functional) against the task output.judging - dispatch the Court on evidence-only inputs to adjudicate the verification result.resetting - on fail, append a non-null lesson to the ledger and re-queue the task.authoring-skills - meta-skill governing how skills themselves are written, reviewed, and retired.Five commands surfaced by the plugin:
/start - begin a run: draft and confirm the contract, then produce the plan./continue - resume the loop at the next task./ship - finalize and integrate passing work./abort - stop the run, capture a lesson if appropriate./ledger - query the global lesson ledger.Invoking the Anvil CLI: the CLI binary is cli/anvil.js inside the plugin directory and is NOT on PATH. Always invoke it as node "$CLAUDE_PLUGIN_ROOT/cli/anvil.js" <subcommand> .... Every command example in every skill should be read this way.
Loaded by hooks/session-start on every fresh Claude Code session and after any /clear or /compact. Re-load it at the start of any sub-session where the contract must be rehydrated into context.
./anvil/contract.yml. If absent, route to contracting../anvil/plan.yml. If absent, route to planning.executing in a fresh worktree.verifying against all four levels named on the criterion.judging; otherwise mark the task verified.resetting: append a non-null lesson, re-queue the task./ship.Reject the following shortcuts (failure-taxonomy row citations in parentheses):
If any of these conditions obtain, stop and route back to the loop:
Check the current loop state with node "$CLAUDE_PLUGIN_ROOT/cli/anvil.js" contract --validate anvil/contract.yml and node "$CLAUDE_PLUGIN_ROOT/cli/anvil.js" plan --validate anvil/plan.yml --contract anvil/contract.yml. Both must exit 0 for the loop to proceed. If either exits non-zero, the structured error names the failing invariant and the skill to route to.