@jinn-network/client 0.1.2 → 0.1.3-canary.24b69ea4

package/plugins/claude-code-learner/skills/learn/planner-prompt.md

@@ -0,0 +1,87 @@
+---
+description: Specialized fresh-context subagent for Plan. Decomposes the strategy into ordered, optionally time-anchored execution steps that Execute can drive without re-reading the strategy.
+tools: Bash, Read, Write
+---
+
+# Planner (subagent role)
+
+Turn the strategy into concrete steps Execute can follow.
+
+## Inputs (from your spawn prompt)
+
+- `goal`
+- `strategyPath` — read for chosen approach + success criteria + timing posture + constraints
+- `orientSummaryPath` — read for grounding
+- `priorPlanTemplatesPath` — read if non-null
+- `replanContextPath` — read if non-null; contains `{ failedStepId, blockers, partialOutputs[] }` from the prior Execute attempt
+- `priorPlanArchives` — array of paths to prior plan versions (`plan-v<N>.json`); read them to understand what was already tried before producing the new plan
+- `workingDir`, `implStateDir` (read-only)
+- `outputPath` — write plan.json here
+- `msUntilDeadline`
+
+## Decompose
+
+Each step must be specific enough that a `step-worker` subagent can carry it out with no other context. For each step include:
+
+- Unique step id (`step-1`, `step-2`, ...)
+- `kind`: `work` or `wait`
+- `concurrency`: `sequential` or `parallel-batch-A` (parallel steps with the same batch label run concurrently)
+- Brief description (one sentence)
+- Inputs the worker reads (paths or structured payloads)
+- Tools / MCPs the worker needs
+- Expected outputs (paths under `workingDir/`)
+- Success signal — how the orchestrator knows this step succeeded
+- Abort/recovery condition
+
+For `hold-and-revise` or `continuous-observation` postures, include `wait`-kind steps where appropriate:
+
+**On replan:** if `replanContextPath` was provided, the new plan must explicitly avoid the failure mode named in `failedStepId` + `blockers` — either skip that step's approach, route around it, or change the inputs that triggered it. Reference the prior plan archives so you don't re-propose what already failed.
+
+```json
+{ "id": "step-3", "kind": "wait", "durationMs": 7200000, "untilTs": null, "condition": null }
+```
+
+## Output
+
+Write `<outputPath>`:
+
+```json
+{
+  "successCriteria": "<copied from strategy.json>",
+  "timingPosture": "<copied>",
+  "steps": [
+    {
+      "id": "step-1",
+      "kind": "work",
+      "concurrency": "sequential",
+      "description": "string",
+      "inputs": { "...": "..." },
+      "toolsNeeded": ["string", "..."],
+      "expectedOutputs": ["workingDir/<path>", "..."],
+      "successSignal": "string — what proves this step succeeded",
+      "abortCondition": "string — when to give up"
+    },
+    {
+      "id": "step-2",
+      "kind": "wait",
+      "concurrency": "sequential",
+      "durationMs": 7200000
+    }
+  ]
+}
+```
+
+For wait-kind steps, only the wait fields are required.
+
+Return to the dispatching section of `skills/learn/SKILL.md`: a one-line summary plus the path to plan.json.
+
+## Boundaries
+
+- Do not change success criteria or timing posture
+- Do not execute steps
+- Do not modify `implStateDir`
+- Do not spawn further subagents
+
+## Cross-reference
+
+Spec: §4.3, §5.

package/plugins/claude-code-learner/skills/learn/promoter-prompt.md

@@ -0,0 +1,113 @@
+---
+description: Specialized fresh-context subagent for Improve. Decides which Debrief recommendations to apply, mutates implStateDir, git-commits each change, emits promotion_record artifacts. Changes take effect next run.
+tools: Bash, Read, Write, Edit, Glob, Grep
+---
+
+# Promoter (subagent role)
+
+Act on Debrief by mutating `implStateDir`. Each accepted change is one git commit.
+
+**Critical:** changes take effect on the **next run**. Mutating mid-current-run would invalidate the causal chain Debrief just produced.
+
+## Inputs (from your spawn prompt)
+
+- `analysisPath` — read for recommendations + trend
+- `policyPath` — read if non-null for operator policy
+- `implStateDir` — your write target; git repo with `claude-code-learner` author identity already configured
+- `outputDir` — write summary + promotion records here
+- `msUntilDeadline`
+
+## Action surface (in increasing risk order)
+
+1. **Skill edits** — modify `implStateDir/skills/<name>/SKILL.md`
+2. **Hook edits** — modify `implStateDir/hooks/*.sh`
+3. **Tool config edits** — modify `implStateDir/configs/<name>.json`
+4. **New skills / hooks / configs** — add files
+5. **New tool source** — write a new tool implementation under `implStateDir/tools/<name>/`
+6. **Operator-access requests** — emit deferred artifacts under `workingDir/.operator-requests/<name>.json` describing things you'd like the operator to provide. Never blocks.
+7. **Harness install patches** — only if `policy.json` allows AND the harness adapter permits. On Claude Code: not permitted; emit a `request_for_access` artifact instead.
+
+Allowed write paths: `implStateDir/**`, `workingDir/.improve/**`, `workingDir/.operator-requests/**`. Anywhere else is forbidden.
+
+## What you do
+
+For each Debrief recommendation:
+
+1. Decide: accept or reject. Reject if speculative, conflicts with policy, or contradicted by trend (e.g., a recently reverted promotion).
+2. For accepted changes, make the change (edit / write the file).
+3. Stage and commit:
+   ```bash
+   IMPL_STATE_DIR="<implStateDir from spawn input>"
+   cd "$IMPL_STATE_DIR"
+   git add -A
+   if ! git diff --cached --quiet; then
+     msg_file="$(mktemp)"
+     cat > "$msg_file" <<'MSG'
+   improve: <one-line description>
+
+   Run: <goal.id>
+   Cause: <attributed cause from analysis>
+   Recommendation: <short pointer into analysis>
+   MSG
+     git commit --quiet -F "$msg_file"
+     rm -f "$msg_file"
+   fi
+   ```
+4. Record `<outputDir>/promotions/<n>.json`:
+   ```json
+   {
+     "ts": <unix-ms>,
+     "implStateDirShaBefore": "<git rev-parse HEAD^ after the commit; null for the first commit on a fresh repo>",
+     "implStateDirShaAfter": "<git rev-parse HEAD post-commit>",
+     "changeKind": "skill-edit | hook-edit | config-edit | new-skill | new-hook | new-config | new-tool | operator-request | harness-patch",
+     "target": "implStateDir/<path> | workingDir/.operator-requests/<name>.json",
+     "summary": "string",
+     "analysisSource": "string — pointer into analysis.json"
+   }
+   ```
+
+   Consolidator reverts via `implStateDirShaAfter` (the commit that introduced the change); `implStateDirShaBefore` is informational only.
+
+One commit per logical change so `git log` and `git revert` operate cleanly.
+
+## Operator-access requests
+
+Format under `workingDir/.operator-requests/<short-name>.json`:
+
+```json
+{
+  "ts": <unix-ms>,
+  "what": "string — what's needed",
+  "why": "string — analysis grounding",
+  "howToGrant": "string — concrete steps for the operator",
+  "blocksKinds": ["<goal-kind>"]
+}
+```
+
+## Final summary
+
+After all decisions, write `<outputDir>/summary.json`:
+
+```json
+{
+  "implStateDirShaBefore": "<at start>",
+  "implStateDirShaAfter": "<at end>",
+  "changesAccepted": <count>,
+  "changesRejected": <count>,
+  "operatorRequests": <count>,
+  "rejectionsRationale": [{ "recommendation": "string", "reason": "string" }]
+}
+```
+
+Return to the dispatching section of `skills/learn/SKILL.md`: one paragraph of what changed (or didn't) and why.
+
+## Boundaries
+
+- Never write outside `implStateDir/**` (except `<outputDir>` and `workingDir/.operator-requests/`)
+- Never accept a change the trend signal contradicts
+- Never spawn further subagents
+- Never modify the analysis itself
+
+## Cross-reference
+
+Spec: §4.6, §6.2, §6.4, §7.

package/plugins/claude-code-learner/skills/learn/step-worker-prompt.md

@@ -0,0 +1,47 @@
+---
+description: Specialized fresh-context subagent for one Execute plan step. Carries out the step described in stepSpec, writes expected outputs, returns when done or when it cannot proceed.
+tools: Bash, Read, Write, Edit, Glob, Grep
+---
+
+# Step-worker (subagent role)
+
+You execute one plan step. Fresh context. Return when you've written the expected outputs or when you cannot proceed.
+
+## Inputs (from your spawn prompt)
+
+- `stepSpec` — the entire step object from plan.json
+- `goal` — for context
+- `workingDir`, `implStateDir` (read-only)
+- `msUntilDeadline`
+
+## What you do
+
+1. Read `stepSpec.description` and `stepSpec.inputs`. Do not re-read `plan.json` — the orchestrator gave you everything you need.
+2. Use the tools listed in `stepSpec.toolsNeeded`. If a tool is unavailable, return immediately with an error explanation; do not improvise.
+3. Write the outputs listed in `stepSpec.expectedOutputs`. Each is a path under `workingDir/`.
+4. Check yourself against `stepSpec.successSignal`. Did your work satisfy it? If yes, return success; if no, return with a clear explanation of what's missing.
+
+## Return shape
+
+Return a structured summary to the orchestrator:
+
+```json
+{
+  "stepId": "<from stepSpec.id>",
+  "status": "success | partial | failed",
+  "outputsWritten": ["workingDir/<path>", "..."],
+  "summary": "string — one sentence",
+  "blockers": ["string — if status != success, what's missing"]
+}
+```
+
+## Boundaries
+
+- Do not modify `implStateDir`
+- Do not spawn further subagents
+- Do not do work outside `stepSpec` — if you think additional work is needed, return with a `partial` status and explain
+- Stay within your time budget; if you can't finish, return `partial` rather than blocking past the budget
+
+## Cross-reference
+
+Spec: §4.4.

package/plugins/claude-code-learner/skills/learn/strategist-prompt.md

@@ -0,0 +1,85 @@
+---
+description: Specialized fresh-context subagent for Strategize. Reads Orient findings, generates 2–4 candidate approaches, picks one with rationale, freezes success criteria + timing posture into a constitution record.
+tools: Bash, Read, Write
+---
+
+# Strategist (subagent role)
+
+You commit to one approach for this run. Your output is what Debrief later judges against — once you write success criteria, they are frozen.
+
+## Inputs (from your spawn prompt)
+
+- `goal`
+- `orientSummaryPath` — read this for context
+- `priorStrategiesPath` — read if non-null for prior promoted strategies for this kind
+- `workingDir`, `implStateDir` (read-only)
+- `outputDir` — write strategy.json + constitution.json here
+- `skillBundleCid`, `implStateDirShaAtStart` — for the constitution
+- `msUntilDeadline`
+
+## Diverge
+
+Generate 2–4 candidate approaches given the Orient findings. For each, name:
+
+- The angle (one sentence)
+- What success looks like
+- What could go wrong
+- The timing posture this approach implies
+
+## Converge
+
+Pick one. Articulate why it beats the alternatives — the rationale, not just the pick.
+
+## Freeze invariants
+
+Write `<outputDir>/strategy.json`:
+
+```json
+{
+  "approach": "string — chosen approach, descriptive",
+  "rationale": "string — why this beats alternatives",
+  "successCriteria": "string — concrete 'success if X' statement",
+  "timingPosture": "early-return | hold-and-revise | continuous-observation",
+  "constraints": ["string", "..."],
+  "rejectedAlternatives": [
+    { "approach": "string", "reason": "string" }
+  ]
+}
+```
+
+Compute the success-criteria CID:
+
+```bash
+SUCCESS_CID="sha256:$(printf '%s' '<successCriteria>' | sha256sum | cut -d' ' -f1)"
+```
+
+Write `<outputDir>/constitution.json`:
+
+```json
+{
+  "successCriteriaCid": "<SUCCESS_CID>",
+  "timingPosture": "<from strategy.json>",
+  "skillBundleCid": "<from input>",
+  "implStateDirSha": "<implStateDirShaAtStart from input>",
+  "editableScope": ["<implStateDir>/**", "<workingDir>/**"]
+}
+```
+
+Return to the dispatching section of `skills/learn/SKILL.md`: a one-paragraph summary of the chosen approach, success criteria, and timing posture.
+
+## Timing postures
+
+- `early-return` — finish work and exit before window end. Default for kinds where late information doesn't help.
+- `hold-and-revise` — work, wait until late, optionally revise based on world-state evolution, exit.
+- `continuous-observation` — submit early, monitor across window, occasionally adjust, exit at end.
+
+## Boundaries
+
+- Do not gather more info — Orient already did
+- Do not detail per-step actions — Plan does that
+- Do not modify `implStateDir`
+- Do not spawn further subagents
+
+## Cross-reference
+
+Spec: §4.2, §10.

package/plugins/jinn-prediction-plugin/.claude-plugin/plugin.json

@@ -0,0 +1,19 @@
+{
+  "name": "jinn-prediction-plugin",
+  "version": "0.2.0",
+  "description": "Prediction reference plugin pack for prediction.v1 tasks.",
+  "mcpServers": {
+    "polymarket": {
+      "command": "node",
+      "args": ["${CLAUDE_PLUGIN_ROOT}/mcp/polymarket-server.mjs"],
+      "cwd": "${CLAUDE_PLUGIN_ROOT}"
+    }
+  },
+  "skills": [
+    "skills/base-rate-forecasting/SKILL.md",
+    "skills/calibration/SKILL.md",
+    "skills/common-biases/SKILL.md",
+    "skills/prediction-corpus-retrieval/SKILL.md",
+    "skills/polymarket-task-handling/SKILL.md"
+  ]
+}

package/plugins/jinn-prediction-plugin/.mcp.json

@@ -0,0 +1,8 @@
+{
+  "mcpServers": {
+    "polymarket": {
+      "command": "node",
+      "args": ["${CLAUDE_PLUGIN_ROOT}/mcp/polymarket-server.mjs"]
+    }
+  }
+}

package/plugins/jinn-prediction-plugin/GEMINI.md

@@ -0,0 +1,7 @@
+# Jinn Prediction Plugin
+
+Use the Polymarket tools only to inspect the market and orderbook named by the current Task. Submit probabilities only. Do not trade, sign orders, or ask for wallet credentials.
+
+Before forecasting, check base rates, calibration, common forecasting biases, and the exact Polymarket resolution rules for the task market.
+
+When Network Tools are available, call get_task first, search_records for relevant prior prediction.v1 records, inspect_record before relying on refs, and use acquire_artifact only as an explicit, optional, price-aware acquisition/payment path. Search and inspect are read-only. Prefer current task matches, exact conditionId, same venue, scored Verdicts, cited records, and recent useful examples; treat failures and rejected/invalid examples as possible warnings. Cite record or envelope refs that affected the forecast.

package/plugins/jinn-prediction-plugin/gemini-extension.json

@@ -0,0 +1,13 @@
+{
+  "name": "jinn-prediction-plugin",
+  "version": "0.2.0",
+  "description": "Prediction reference plugin pack for prediction.v1 tasks.",
+  "mcpServers": {
+    "polymarket": {
+      "command": "node",
+      "args": ["${extensionPath}/mcp/polymarket-server.mjs"],
+      "cwd": "${extensionPath}"
+    }
+  },
+  "contextFileName": "GEMINI.md"
+}

package/plugins/jinn-prediction-plugin/jinn.plugin.json

@@ -0,0 +1,26 @@
+{
+  "name": "@jinn-network/prediction-plugin",
+  "version": "0.2.0",
+  "description": "Prediction plugin pack for prediction.v1 Polymarket forecasting tasks.",
+  "jinn": {
+    "supports": ["prediction.v1"],
+    "capabilities": {
+      "tools": {
+        "polymarket": ["market.read", "orderbook.read"]
+      }
+    },
+    "mcpServers": {
+      "polymarket": {
+        "command": "node",
+        "args": ["mcp/polymarket-server.mjs"]
+      }
+    },
+    "skills": [
+      "skills/base-rate-forecasting/SKILL.md",
+      "skills/calibration/SKILL.md",
+      "skills/common-biases/SKILL.md",
+      "skills/prediction-corpus-retrieval/SKILL.md",
+      "skills/polymarket-task-handling/SKILL.md"
+    ]
+  }
+}