Merge pull request 'feat(plugin): make using-scribe skill actively pull standing rules' (#66) from dev into main

This commit was merged in pull request #66.
This commit is contained in:
2026-06-10 02:20:28 -04:00
2 changed files with 19 additions and 44 deletions
+19 -6
View File
@@ -1,6 +1,6 @@
---
name: using-scribe
description: Use at the start of any session and before answering questions about the operator's work or starting a task — establishes the Scribe-first reflex (recall before acting, load standing rules, update over duplicate, plan in Scribe not in files).
description: Use at the START of every session, and before answering anything about the operator's work or starting any task — establishes the Scribe-first reflex. FIRST ACTION of a session: call list_always_on_rules() (and enter_project when a repo/project is in scope) to load the operator's binding rules. Then recall before acting, update over duplicate, plan in Scribe not in files.
---
# Using Scribe
@@ -10,6 +10,20 @@ milestones, events, typed entities) and rulebook, reachable through the bundled
`scribe` MCP server. Its value is mostly in what it **already holds** — so make
reading it a reflex, not something you wait to be asked for.
## Do this first (every session)
**Pull the standing rules yourself — do not wait for them to be handed to you.**
At the start of a session, before substantive work, call
`list_always_on_rules()` to load the operator's always-on rules. If the working
repo maps to a Scribe project (you're in a known repo, or `list_repo_bindings`
shows a binding), call `enter_project(id)` instead/as-well — it returns the
project plus its applicable rules, open tasks, and recent notes in one shot.
Do this actively. A SessionStart hook *may* also inject a rule index, but treat
that as a bonus, not a precondition: it can be absent (e.g. when the instance is
unreachable, or the token didn't reach the hook), so the reliable path is this
explicit pull. Rules loaded this way are **binding** for the session.
## The reflex
1. **Recall before acting.** Before answering a question about the operator's
@@ -18,11 +32,10 @@ reading it a reflex, not something you wait to be asked for.
re-deriving it or opening a duplicate. When a project is in scope, pass its
`project_id` so results stay scoped.
2. **Standing rules are binding.** The SessionStart context lists the operator's
always-on rule titles. Treat them as binding. Pull full text with
`list_always_on_rules()` or `get_rule(id)` when a rule is about to bite.
When a project is in scope, `enter_project(id)` also returns its applicable
rules.
2. **Standing rules are binding.** Load them via `list_always_on_rules()` at
session start (see "Do this first"); treat every one as binding. Pull a
rule's full statement with `get_rule(id)` when it's about to bite. When a
project is in scope, `enter_project(id)` also returns its applicable rules.
3. **Update over duplicate.** When recording, prefer updating an existing
note/rule/task over creating a new one. Search first; revise what's there.
-38
View File
@@ -1,38 +0,0 @@
#!/usr/bin/env bash
# Scribe SessionStart hook (dogfood / pre-plugin).
#
# Curls the running Scribe dev instance for the operator's always-on rules +
# active-project context and emits it as SessionStart `additionalContext` — the
# push channel that lets Scribe surface reflexively (plan #755, Phase 1).
#
# FAIL-OPEN by design: any missing tool, missing config, network error, or
# unreachable instance results in injecting nothing and exiting 0. A session
# must NEVER be blocked because Scribe is down. Reads URL+token from the
# project's .mcp.json so no secret lives in this tracked script.
#
# Superseded in Phase 2 by the same hook bundled in the Scribe plugin, where
# URL+token come from plugin userConfig instead of .mcp.json.
set -uo pipefail
MCP_JSON="${CLAUDE_PROJECT_DIR:-.}/.mcp.json"
command -v jq >/dev/null 2>&1 || exit 0
command -v curl >/dev/null 2>&1 || exit 0
[ -f "$MCP_JSON" ] || exit 0
# scribe-dev is the locally-wired instance (prod id 2 / dev id 3 per binding).
url=$(jq -r '.mcpServers["scribe-dev"].url // empty' "$MCP_JSON" 2>/dev/null) || exit 0
auth=$(jq -r '.mcpServers["scribe-dev"].headers.Authorization // empty' "$MCP_JSON" 2>/dev/null) || exit 0
token=${auth#Bearer }
[ -n "$url" ] && [ -n "$token" ] || exit 0
base=${url%/mcp}
body=$(curl -fsS --max-time 8 \
-H "Authorization: Bearer ${token}" \
"${base}/api/plugin/context?project_id=3" 2>/dev/null) || exit 0
text=$(printf '%s' "$body" | jq -r '.context // empty' 2>/dev/null) || exit 0
[ -n "$text" ] || exit 0
jq -n --arg c "$text" \
'{hookSpecificOutput: {hookEventName: "SessionStart", additionalContext: $c}}'
exit 0