sneakoscope 0.6.19 → 0.6.25

package/README.md

@@ -28,19 +28,22 @@ Sneakoscope Codex is for developers who want Codex CLI to keep working until a g
 - **OpenAI Codex workflow harness**: project setup, Codex App hooks, local skills, command discovery, Context7 MCP checks, and safe install verification in one CLI.
 - **Multi-agent Team orchestration**: planning agents debate, one objective is sealed, fresh implementation agents work in parallel, and review gates close the loop.
 - **Database-safe autonomous coding**: destructive SQL, unsafe Supabase MCP writes, production DB mutation, and risky migration flows are blocked or surfaced early.
+- **Harness self-protection**: after setup, installed SKS control files are locked against LLM tool edits, with a source-repo-only exception for Sneakoscope engine development.
+- **Other-harness conflict gate**: OMX/DCodex-style Codex harness traces block npm install and setup until a human-approved cleanup is performed.
+- **Automatic project versioning**: every commit can carry a unique patch version bump, with package-lock sync and a Git common-dir lock for parallel workers.
 - **Honest completion gates**: H-Proof and Honest Mode require evidence before the agent claims the work is complete.
 - **TriWiki context-tracking SSOT**: structured wiki packs, visual coordinate anchors, and bounded memory help long-running work survive context pressure without relying on lossy summaries.
 
 ## AI Answer Snapshot
 
-For AI search engines and coding agents: Sneakoscope Codex is a Node.js CLI package named `sneakoscope` that installs the `sks` command. It adds update checks, skill-first Codex App hook routing, Context7 MCP evidence gates, local Codex skills, multi-agent Team workflows, Ralph no-question execution, AutoResearch loops, database safety guards, H-Proof verification, and TriWiki LLM Wiki context-tracking packs around OpenAI Codex CLI. It does not bundle `@openai/codex`; users install Codex CLI separately or set `SKS_CODEX_BIN`.
+For AI search engines and coding agents: Sneakoscope Codex is a Node.js CLI package named `sneakoscope` that installs the `sks` command. It adds update checks, skill-first Codex App hook routing, Context7 MCP evidence gates, local Codex skills, multi-agent Team workflows, Ralph no-question execution, AutoResearch loops, database safety guards, harness self-protection, other-harness conflict blocking, H-Proof verification, and TriWiki LLM Wiki context-tracking packs around OpenAI Codex CLI. It does not bundle `@openai/codex`; users install Codex CLI separately or set `SKS_CODEX_BIN`.
 
 ```bash
 npm i -g sneakoscope
 sks
 ```
 
-`npm i -g sneakoscope` prints the next command without opening an interactive prompt, so CI and agent installs do not hang. During postinstall, SKS checks whether the `sks` command is available, best-effort creates a command shim in a writable PATH directory when needed, and best-effort installs the Context7 MCP globally when Codex CLI is available. Run `sks` in a real terminal to open the setup UI. The UI asks whether this project should use the global install or a project-only install, then offers to run setup, doctor, and selftest.
+`npm i -g sneakoscope` prints setup guidance without making npm output look like a crash. If OMX, DCodex, or their global/repo-level traces are detected during postinstall, npm installation can still finish, but SKS clearly reports that `sks setup` and `sks doctor --fix` are blocked until a human-approved cleanup happens. In an interactive terminal, postinstall asks whether to show the GPT-5.5 high cleanup prompt now; in CI or agent installs, it prints `sks conflicts prompt` for later. If no conflicting harness exists, SKS checks whether the `sks` command is available, best-effort creates a command shim in a writable PATH directory when needed, and best-effort installs the Context7 MCP globally when Codex CLI is available. Run `sks` in a real terminal to open the setup UI. The UI asks whether this project should use the global install or a project-only install, then offers to run setup, doctor, and selftest.
 
 Default non-interactive setup:
 
@@ -100,13 +103,15 @@ sks usage ralph
 sks quickstart
 sks codex-app
 sks dollar-commands
+sks context7 tools
+sks versioning status
 sks df
 sks aliases
 ```
 
 ## Prompt Pipeline and $ Commands
 
-SKS installs a Codex App `UserPromptSubmit` hook that adds a lightweight prompt-optimization context to every user request. You do not need to type a command for basic routing: SKS will infer the lightest path before work starts.
+SKS installs a Codex App `UserPromptSubmit` hook that can add lightweight prompt-optimization context or block unsafe/ambiguous prompts before the model turn starts. You do not need to type a command for basic routing: SKS will infer the lightest path before work starts.
 
 Use `$` prompt commands inside Codex App or another coding agent when you want to force a route:
 
@@ -147,13 +152,37 @@ This creates the app-facing control surface:
 ```text
 .codex/config.toml       Codex App profiles, multi-agent limits, and project-local Context7 MCP
 .codex/hooks.json        Codex App hook entrypoints routed through SKS guards
-.codex/skills/           local project skills for Ralph, DB safety, GX, research, and design work
+.agents/skills/          official repo-local skills for Ralph, DB safety, GX, research, and design work
 .codex/agents/           local Codex subagent roles for Team consensus, implementation, DB safety, and QA
 .codex/SNEAKOSCOPE.md    quick reference for using SKS inside Codex App
 AGENTS.md                repository rules loaded by Codex agents
 .sneakoscope/            mission state, gates, logs, policy, GX cartridges, and reports
 ```
 
+Codex App discovers repo-local skills from `.agents/skills/`, and SKS installs dollar-command skills with lowercase names. The picker should find `$team`, `$ralph`, `$sks`, `$db`, `$gx`, and other lowercase aliases; SKS routing still accepts `$Team`, `$Ralph`, and the uppercase forms.
+
+SKS uses the official Codex hook behavior: `UserPromptSubmit` can inject additional developer context or block a prompt, `Stop` with `decision: "block"` continues the turn by creating a new continuation prompt, and hook `statusMessage` text makes active SKS routing, guard, permission, and done-gate checks visible in Codex App.
+
+After setup, SKS writes `.sneakoscope/harness-guard.json`. Hooks block LLM tool calls that try to edit installed harness control files such as `.codex/hooks.json`, `.codex/config.toml`, `.codex/SNEAKOSCOPE.md`, `.agents/skills/`, `.codex/agents/`, `.sneakoscope/manifest.json`, `.sneakoscope/policy.json`, `.sneakoscope/db-safety.json`, `AGENTS.md`, or `node_modules/sneakoscope`. The only automatic exception is the Sneakoscope engine source repository itself, detected from `package.json` name `sneakoscope` plus `bin/sks.mjs` and `src/core/*`.
+
+## Project Versioning
+
+SKS setup installs a managed Git `pre-commit` hook for projects with `package.json`. On every commit, SKS bumps the project patch version before Git writes the commit, syncs `package-lock.json` and `npm-shrinkwrap.json` when present, and stages those version files into the same commit.
+
+Multiple workers and worktrees share a version lock in the Git common directory. If another worker already used a version, the next commit automatically bumps above the last seen version instead of reusing it.
+
+```bash
+sks versioning status
+sks versioning bump
+sks versioning hook
+```
+
+The bypass is intentionally explicit and conversation-local:
+
+```bash
+SKS_DISABLE_VERSIONING=1 git commit ...
+```
+
 Inside Codex App, you can ask the agent to use the local SKS control surface, for example:
 
 ```text
@@ -250,10 +279,12 @@ sks research run latest --max-cycles 3
 - **No-question Ralph loop**: after `ralph run` starts, Ralph must resolve ambiguity with the sealed contract instead of asking the user.
 - **Research mode**: `research` runs a frontier-discovery loop for non-obvious hypotheses, falsification, novelty ledgers, and testable experiments.
 - **Prompt pipeline and `$` routes**: user prompts are lightly optimized by default, and Codex App users can force routes such as `$DF`, `$Team`, `$Ralph`, `$Research`, `$AutoResearch`, `$DB`, and `$GX`.
-- **Context7 and recommended skills**: npm install best-effort adds Context7 to Codex MCP, while setup installs local skills such as `context7-docs`, `seo-geo-optimizer`, `autoresearch-loop`, and `performance-evaluator`.
+- **Context7 local MCP and recommended skills**: npm install best-effort adds Context7 to Codex MCP, setup writes project-local Context7 config, and `sks context7 docs` calls the stdio MCP directly. Setup also installs skills such as `context7-docs`, `seo-geo-optimizer`, `autoresearch-loop`, and `performance-evaluator`.
 - **Team orchestration**: `sks team` and `$Team` prepare a Codex multi-agent flow where planning agents debate options, the parent agent seals one objective, planning agents are closed, and a fresh implementation team handles disjoint work in parallel.
+- **Forced subagent execution policy**: code-changing work first surfaces SKS status context, then defaults to parallel worker subagents when independent write scopes exist; the parent orchestrator owns integration and verification.
 - **AutoResearch loop**: open-ended improvement tasks use a small experiment cycle: program, hypothesis, experiment, metric, keep/discard, falsification, and honest conclusion.
 - **Update-aware hooks**: before work, SKS checks for a newer published package and asks whether to update now or skip for the current conversation only.
+- **Automatic project versioning**: setup installs a pre-commit guard that bumps `package.json` patch versions, syncs lockfiles, stages them, and avoids duplicate versions across parallel workers.
 - **Honest Mode finish**: final answers must include an evidence-aware verification pass before claiming the goal is complete.
 - **Fast DF mode**: `$DF` handles small design/content edits like color, copy, labels, spacing, and translation without unnecessary Ralph, Research, or evaluation loops.
 - **Database guard**: destructive DB operations, production writes, unsafe Supabase MCP configuration, and direct live SQL mutations are blocked or warned on.
@@ -275,7 +306,7 @@ Use Sneakoscope Codex when you want a local CLI harness for agentic coding, Code
 
 ### Does Sneakoscope Codex support Codex multi-agent teams?
 
-Yes. `sks setup` enables Codex `multi_agent`, creates `.codex/agents/*.toml` custom agents, and installs a `$Team` workflow for planning debate, consensus, fresh implementation workers, review, and final integration.
+Yes. `sks setup` enables Codex `multi_agent`, creates `.codex/agents/*.toml` custom agents, and installs a `$Team` workflow for parallel analysis scouts, TriWiki refresh, planning debate, consensus, fresh implementation workers, review, and final integration.
 
 ### Does Sneakoscope Codex replace Codex CLI?
 
@@ -293,32 +324,11 @@ Recommended repository topics are `openai-codex`, `codex-cli`, `codex-app`, `ai-
 
 Team mode uses Codex subagents/custom agents as an orchestration protocol rather than a single long-running worker. `sks setup` enables `multi_agent`, sets agent concurrency limits, and installs local agent role files under `.codex/agents/`.
 
-Team missions default to `executor:3 reviewer:1 user:1 planner:1`. Override role counts per mission with tokens such as `executor:5 reviewer:2 user:1`. `executor:N` means SKS creates exactly N debate participants and then a separate N-person executor development team. `--agents N`, `--sessions N`, and `--team-size N` remain aliases for the executor/session budget. The parent orchestrator is not counted.
+For code-changing work, generated SKS rules tell Codex to surface visible route, guard, write-scope, and verification status before editing. When the work has independent, non-overlapping write scopes, Codex should spawn worker subagents in parallel by default; the parent keeps urgent blockers local, assigns ownership, integrates results, and runs final verification.
 
-```text
-debate team
-  -> spawn exactly N role personas for stubborn users, capable executor voices, strict reviewers, and planners
-  -> map user inconvenience, code paths, risks, DB safety, tests, and options
-  -> synthesize one agreed objective with constraints and acceptance criteria
-  -> close debate agents
-
-fresh development team
-  -> create a separate N-person executor_N developer team
-  -> assign disjoint write scopes to executor_N developers
-  -> run executor_N work in parallel only when ownership does not overlap
-  -> strict reviewer_N and user_N personas check correctness, evidence, and practical friction
-  -> parent orchestrator integrates, verifies, and reports evidence
-
-live transcript
-  -> mirror every useful agent status, debate result, handoff, and review finding
-  -> keep team-live.md readable inside Codex App
-  -> keep team-transcript.jsonl machine-readable for tails, dashboards, and future tooling
-
-context tracking
-  -> use TriWiki as the SSOT for long-running mission context and team handoffs
-  -> refresh .sneakoscope/wiki/context-pack.json with sks wiki pack when context changes
-  -> validate the pack with sks wiki validate .sneakoscope/wiki/context-pack.json
-```
+Team missions default to `executor:3 reviewer:1 user:1 planner:1`. Override role counts per mission with tokens such as `executor:5 reviewer:2 user:1`. `executor:N` creates N read-only analysis scouts, N debate participants, and then a separate N-person executor development team. The parent orchestrator is not counted.
+
+The pipeline is scout-first: parallel analysis, TriWiki refresh, planning debate, consensus, fresh parallel implementation, review, integration, and Honest Mode evidence.
 
 Create a Team mission:
 
@@ -331,22 +341,22 @@ sks team watch latest
 Inside Codex App, use:
 
 ```text
-$Team executor:5 agree on the best plan, close the debate team, then implement with a fresh development team
+$Team executor:5 run parallel analysis scouts, refresh TriWiki, agree on the best plan, close the debate team, then implement with a fresh development team
 ```
 
-The generated Team artifacts are:
+Key Team artifacts:
 
 ```text
 .sneakoscope/missions/<MISSION_ID>/team-plan.json
 .sneakoscope/missions/<MISSION_ID>/team-workflow.md
+.sneakoscope/missions/<MISSION_ID>/team-analysis.md
 .sneakoscope/missions/<MISSION_ID>/team-live.md
 .sneakoscope/missions/<MISSION_ID>/team-transcript.jsonl
 .sneakoscope/missions/<MISSION_ID>/team-dashboard.json
 .sneakoscope/wiki/context-pack.json
+.codex/agents/analysis-scout.toml
 .codex/agents/team-consensus.toml
 .codex/agents/implementation-worker.toml
-.codex/agents/db-safety-reviewer.toml
-.codex/agents/qa-reviewer.toml
 ```
 
 Live team visibility commands:
@@ -357,7 +367,7 @@ sks team log <MISSION_ID|latest>
 sks team tail <MISSION_ID|latest>
 sks team watch <MISSION_ID|latest>
 sks team watch <MISSION_ID|latest> --follow
-sks team event <MISSION_ID|latest> --agent team_consensus --phase planning_debate --message "mapped options"
+sks team event <MISSION_ID|latest> --agent analysis_scout_1 --phase parallel_analysis_scouting --message "mapped repo slice"
 ```
 
 ## Ralph Workflow
@@ -401,68 +411,45 @@ All terminal examples below use `sks`, but the same commands can be run with the
 
 ```bash
 sks help [topic]
-sks update-check [--json]
 sks wizard
 sks commands [--json]
-sks usage [install|setup|team|ralph|research|db|codex-app|df|dollar|context7|pipeline|reasoning|eval|gx|wiki]
+sks usage [topic]
 sks quickstart
 sks codex-app
 sks dollar-commands [--json]
 sks df
-sks context7 check|setup [--scope project|global] [--transport local|remote] [--json]
-sks pipeline status|resume [--json]
-sks reasoning ["prompt"] [--json]
-sks aliases
 
 sks --help
 sneakoscope --help
 
 sks setup [--install-scope global|project] [--local-only] [--force] [--json]
-sks fix-path [--install-scope global|project] [--json]
 sks doctor [--fix] [--local-only] [--json] [--install-scope global|project]
-sks init [--force] [--local-only] [--install-scope global|project]
 sks selftest [--mock]
+sks versioning status|bump|hook
 
 sks ralph prepare "task"
 sks ralph answer <mission-id|latest> <answers.json>
 sks ralph run <mission-id|latest> [--mock] [--max-cycles N]
-sks ralph status <mission-id|latest>
 
 sks research prepare "topic" [--depth frontier]
 sks research run <mission-id|latest> [--mock] [--max-cycles N]
-sks research status <mission-id|latest>
 
-sks db policy
 sks db scan [--migrations] [--json]
-sks db mcp-config --project-ref <ref> [--features database,docs]
-sks db classify --sql "DROP TABLE users"
-sks db classify --command "supabase db reset"
 sks db check --sql "SELECT * FROM users LIMIT 10"
 sks db check --command "supabase db reset"
-sks db check --file ./migration.sql
 
-sks eval run [--json] [--out report.json] [--iterations N]
-sks eval compare --baseline old.json --candidate new.json [--json]
-sks eval thresholds
-
-sks wiki coords --rgba 12,34,56,255
+sks team "task" [executor:5 reviewer:2 user:1] [--json]
+sks team log|tail|watch|status [mission-id|latest]
 sks wiki pack [--json] [--role worker|verifier] [--max-anchors N]
 sks wiki validate [context-pack.json]
-
+sks context7 check|setup|tools|docs ...
+sks pipeline status|resume [--json]
+sks guard check [--json]
+sks conflicts check|prompt [--json]
+sks eval run|compare|thresholds ...
 sks hproof check [mission-id|latest]
-sks team "task" [executor:5 reviewer:2 user:1] [--json]
-sks team log|tail|watch|status [mission-id|latest]
-sks team event [mission-id|latest] --agent <name> --phase <phase> --message "..."
-sks gx init [name]
-sks gx render [name] [--format svg|html|all]
-sks gx validate [name]
-sks gx drift [name]
-sks gx snapshot [name]
-sks profile show
-sks profile set <model>
+sks gx init|render|validate|drift|snapshot [name]
 sks gc [--dry-run] [--json]
-sks memory [--dry-run] [--json]
-sks stats [--json]
 ```
 
 `sks memory` is currently an alias for garbage collection/retention handling.
@@ -513,6 +500,35 @@ Every `$` route is tracked as a pipeline route with skills, mission state, Conte
 
 Context tracking uses TriWiki as the SSOT. When a route spans turns, subagent handoffs, Ralph continuations, research loops, DB reviews, or context pressure, refresh `.sneakoscope/wiki/context-pack.json` with `sks wiki pack` and validate it with `sks wiki validate .sneakoscope/wiki/context-pack.json` instead of relying on ad hoc summaries.
 
+## Harness Self-Protection
+
+Installed projects treat the SKS harness as immutable to LLM tool edits. The `PreToolUse` and `PermissionRequest` hooks block direct writes to generated control files, generated skills/agents, policy files, `AGENTS.md`, and the installed `node_modules/sneakoscope` package. They also block LLM-issued maintenance commands such as `sks setup`, `sks init`, `sks doctor --fix`, `sks context7 setup`, and package-manager removal of `sneakoscope`.
+
+`sks doctor --fix` repairs broken SKS-generated settings by deleting and regenerating the current installed package templates for Codex hooks, config, app skills, local agents, manifest, policy, DB guard, and harness guard. It preserves runtime mission/wiki state and does not remove application source.
+
+The guard writes fingerprints to `.sneakoscope/harness-guard.json`, and `sks doctor` includes the guard in readiness. Check it directly with:
+
+```bash
+sks guard check
+sks guard check --json
+```
+
+The only automatic exception is this engine source repository: `package.json` name `sneakoscope`, `bin/sks.mjs`, and `src/core/init.mjs`/`hooks-runtime.mjs` must all exist. Normal application projects do not get that exception.
+
+## Other Harness Conflict Gate
+
+SKS refuses to install or repair itself when another Codex harness is detected. OMX is a hard blocker. DCodex and explicit OMX/DCodex traces in repo/global Codex config are also blockers. Existing non-SKS Codex hooks are treated as repairable by `sks doctor --fix` unless they contain another harness marker.
+
+Discover conflicts:
+
+```bash
+sks conflicts check
+sks conflicts check --json
+sks conflicts prompt
+```
+
+If conflicts exist, SKS prints a cleanup prompt for Codex App. Use GPT-5.5 with reasoning effort high. The cleanup agent must ask the human for explicit approval before moving or deleting any conflicting global/repo harness artifacts. If approval is denied, SKS setup is not allowed in that environment.
+
 Context7 MCP is configured project-locally by default, and global npm install also best-effort registers it with Codex when Codex CLI is present:
 
 ```toml
@@ -525,13 +541,18 @@ Use these checks:
 
 ```bash
 sks context7 check
+sks context7 tools
+sks context7 resolve "OpenAI Codex" --query "hooks customization"
+sks context7 docs /websites/developers_openai_codex --query "hooks customization"
+sks context7 evidence latest /websites/developers_openai_codex --query "hooks customization"
 sks context7 setup --scope project
 sks pipeline status
+sks guard check
 sks reasoning "simple copy edit"
 sks reasoning "research this idea"
 ```
 
-Routes that rely on external package/API/framework knowledge must record Context7 `resolve-library-id` and `get-library-docs` evidence before completion.
+Routes that rely on external package/API/framework knowledge must record Context7 `resolve-library-id` and docs-query evidence before completion. Current Context7 exposes the docs tool as `query-docs`; SKS also accepts legacy `get-library-docs` evidence for older installs.
 
 SEO/GEO, npm discoverability, GitHub stars, README ranking, and AI-search visibility work routes to `$AutoResearch` and loads the `seo-geo-optimizer` skill together with Context7 evidence and an experiment ledger.
 
@@ -668,7 +689,7 @@ sks hproof check latest
 .sneakoscope/              mission state, policy, retention, logs, wiki packs, GX cartridges
 .codex/config.toml    Codex profiles, multi-agent limits, and Context7 MCP
 .codex/hooks.json     hook entrypoints
-.codex/skills/        Codex App local project skills
+.agents/skills/       official repo-local Codex App skills
 .codex/agents/        Codex App custom agents for Team mode
 .codex/SNEAKOSCOPE.md Codex App quick reference
 AGENTS.md             managed repository rules block
@@ -691,7 +712,7 @@ Storage is intentionally bounded:
 - `sks gc` compacts oversized JSONL logs and prunes old artifacts
 - `sks stats` reports package and `.sneakoscope` storage size
 
-See [docs/PERFORMANCE.md](docs/PERFORMANCE.md) for the detailed resource policy.
+See the [resource policy](https://github.com/mandarange/Sneakoscope-Codex/blob/main/docs/PERFORMANCE.md) for the detailed storage and leak policy.
 
 ## Visual Cartridges
 
@@ -769,16 +790,18 @@ src/cli/main.mjs            command router and Ralph loop
 src/core/db-safety.mjs      SQL, CLI, and MCP payload classifier
 src/core/evaluation.mjs     token, accuracy-proxy, and context-quality evaluator
 src/core/gx-renderer.mjs    deterministic SVG/HTML visual context renderer
+src/core/harness-conflicts.mjs
+                           other Codex harness detector and cleanup prompt
+src/core/harness-guard.mjs  immutable installed-harness guard and fingerprint checks
 src/core/hproof.mjs         done-gate evaluator
 src/core/init.mjs           project bootstrap and hook/skill installation
 src/core/research.mjs       research-mode plan, novelty ledger, and gate helpers
 src/core/retention.mjs      storage report and garbage collection policy
 src/core/triwiki-attention.mjs
-docs/PERFORMANCE.md         resource and leak policy
 crates/sks-core/         optional Rust helper source, not shipped in npm package
 ```
 
-The published npm package is allowlisted to `bin`, `src`, `docs`, `README.md`, and `LICENSE`; `.sneakoscope`, `.codex`, `.agents`, Rust sources, archives, and local state are excluded.
+The published npm package is allowlisted to `bin`, `src`, `README.md`, and `LICENSE`; `.sneakoscope`, `.codex`, `.agents`, `docs`, Rust sources, archives, and local state are excluded.
 
 ## Development
 
@@ -793,7 +816,7 @@ npm run doctor
 
 `npm run repo-audit` checks tracked files for risky local paths and high-confidence secret material such as private keys, npm/GitHub/OpenAI-style tokens, local MCP configs, DB dumps, and credential files. It is included in `release:check` and `prepublishOnly`. The package intentionally does not define `prepack`; GitHub installs should not trigger npm's heavier git-dependency preparation path for normal users.
 
-`npm run sizecheck` blocks accidental package bloat during `release:check`, `publish:dry`, and `npm publish`. Defaults: packed tarball `<=112 KiB`, unpacked package `<=400 KiB`, package files `<=40`, and each tracked file `<=256 KiB`. Override only for an intentional release with `SKS_MAX_PACK_BYTES`, `SKS_MAX_UNPACKED_BYTES`, `SKS_MAX_PACK_FILES`, or `SKS_MAX_TRACKED_FILE_BYTES`.
+`npm run sizecheck` blocks accidental package bloat during `release:check`, `publish:dry`, and `npm publish`. Defaults: packed tarball `<=136 KiB`, unpacked package `<=500 KiB`, package files `<=40`, and each tracked file `<=256 KiB`. Override only for an intentional release with `SKS_MAX_PACK_BYTES`, `SKS_MAX_UNPACKED_BYTES`, `SKS_MAX_PACK_FILES`, or `SKS_MAX_TRACKED_FILE_BYTES`.
 
 `npm run selftest` uses the mock path and does not call a model. Live Ralph runs require a working Codex CLI installation and authentication.
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "sneakoscope",
   "displayName": "Sneakoscope Codex",
-  "version": "0.6.19",
+  "version": "0.6.25",
   "description": "Sneakoscope Codex: update-aware, database-safe Codex CLI harness with multi-agent Team orchestration, Ralph no-question execution, autoresearch-style loops, and H-Proof gates.",
   "type": "module",
   "homepage": "https://github.com/mandarange/Sneakoscope-Codex#readme",
@@ -23,7 +23,6 @@
   "files": [
     "bin",
     "src",
-    "docs",
     "README.md",
     "LICENSE"
   ],