fdeops 3.11.0 → 3.11.1

package/README.md

@@ -41,9 +41,11 @@ Nothing to install to see it on a fake client: `npx fdeops demo`.
 ```
 
 ```bash
-npx skills add suboss87/fdeops          # Cursor, Codex, skills-compatible hosts
+npx skills add suboss87/fdeops --skill fde   # Cursor, Codex, skills-compatible hosts
 ```
 
+That is one skill, not a catalogue - `@fde` routes the whole method. The CLI needs no install either: the skill reaches for `npx fdeops` when `fde` is not on the PATH. (Drop `--skill fde` and you also get `testing-fieldbook`, which is for people contributing to this repo, not for field work.)
+
 Claude Code additionally gets session hooks, so context arrives before you type. Everywhere else it is the same fieldbook, loaded when you ask.
 
 **2. Bind once** in the client workspace:

package/bin/check.js

@@ -270,6 +270,22 @@ if (!readme.includes('fde-engagements') || !/fdeops.*init.*engagement/i.test(rea
   fail('README must document fde-engagements + init flow')
 } else ok('README engagement path')
 
+// The contributor-only testing skill lives in .agents/skills/, so a bare
+// `skills add` installs it too. The advertised command must name the one skill
+// a field user wants.
+for (const m of readme.match(/^.*npx skills add .*$/gm) || []) {
+  if (!m.includes('--skill fde')) {
+    fail(`README skills-add command must pin --skill fde: ${m.trim()}`)
+  }
+}
+ok('README skills install is one skill')
+
+// A skill-only install has no fde on the PATH; the router must reach npx before
+// falling back to writing memory by hand.
+if (!read('skills/fde/SKILL.md').includes('npx --yes fdeops')) {
+  fail('skills/fde/SKILL.md must fall back to npx --yes fdeops when the CLI is not installed')
+} else ok('SKILL.md npx CLI fallback')
+
 if (!fs.existsSync(path.join(root, 'docs', 'USAGE.md'))) {
   fail('docs/USAGE.md missing')
 } else ok('docs/USAGE.md')

package/mcp/fdeops-ingest/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fdeops-ingest-mcp",
-  "version": "3.11.0",
+  "version": "3.11.1",
   "private": true,
   "description": "Thin stdio MCP sink for FDEOps ingest (stage → propose → apply). Zero runtime dependencies.",
   "bin": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fdeops",
-  "version": "3.11.0",
+  "version": "3.11.1",
   "description": "Field kit for engineers embedded in client work - a real CLI (recon, memory, portfolio), one @fde skill with field judgment on top, and hooks that make it automatic. Claude Code plugin and any agent that loads skills.",
   "bin": {
     "fdeops": "bin/install.js",

package/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "fdeops",
-  "version": "3.11.0",
+  "version": "3.11.1",
   "description": "Engagement fieldbook for Forward Deployed Engineers: per-client memory in local .fde/ files, one @fde skill, land to close methodology. Local-only, no network.",
   "author": {
     "name": "Subash Natarajan",

package/skills/fde/SKILL.md

@@ -74,7 +74,7 @@ When NOT to interrogate or challenge: unambiguous one-liners, mechanical ops, FD
 - Data tagged `<private>` (sacred data, PHI, cardholder, classified) is **redacted from CLI, dashboard, and hook-injected context**. Do **not** open raw `<private>` blocks with file tools (that bypasses redaction) or paste them into prompts/subagents - work around them, never with them.
 - Locked-down engagement (no AI on their code)? Use the CLI + the fieldbook only. The memory layer is the FDE's own notes, not customer code.
 
-**Engagement path - zero ceremony.** Run `fde resume` (fallback: `node ~/.claude/fdeops/fde.js resume`). The **workspace registry** (written once by `fde resume --init <name>`) is the normal path; resolution order is env var override → registry → pointer file → workspace-name match (read-only) → `./.fde`. Writes require a bind (or `FDEOPS_ENGAGEMENT`), not folder name alone. It prints a **bounded** view of `context.md` - the curated head (state, next action) plus the most recent activity, with the older session log collapsed (use `fde resume --full` when you genuinely need the whole history). If it reports NO ENGAGEMENT: confirm the client name in conversation (one question), then run `fde resume --init <name>` yourself - the one setup step; the FDE never runs setup commands. Never install fdeops on infrastructure the FDE does not control.
+**Engagement path - zero ceremony.** Run `fde resume` (fallbacks, in order: `node ~/.claude/fdeops/fde.js resume`, then `npx --yes fdeops resume` - the CLI is one command away on any machine with Node, so reach for it before doing memory work by hand). The **workspace registry** (written once by `fde resume --init <name>`) is the normal path; resolution order is env var override → registry → pointer file → workspace-name match (read-only) → `./.fde`. Writes require a bind (or `FDEOPS_ENGAGEMENT`), not folder name alone. It prints a **bounded** view of `context.md` - the curated head (state, next action) plus the most recent activity, with the older session log collapsed (use `fde resume --full` when you genuinely need the whole history). If it reports NO ENGAGEMENT: confirm the client name in conversation (one question), then run `fde resume --init <name>` yourself - the one setup step; the FDE never runs setup commands. Never install fdeops on infrastructure the FDE does not control.
 
 **You run the `fde` CLI for deterministic work - never improvise shell, never hand the command to the FDE:**
 
@@ -96,7 +96,7 @@ When NOT to interrogate or challenge: unambiguous one-liners, mechanical ops, FD
 
 **The debrief verb.** Highest-frequency loop. When the FDE shares notes or says "debrief": **you** run the smart path (write notes to a temp file if needed). `--smart` writes a propose file via deterministic heuristics (existing prefixes + light keywords); authentic rambling notes often land mostly in context until **you** rewrite lines with type prefixes. Show the proposed routing in plain language. Only `--apply` (or pipe prefixed lines) after they confirm. Never ask them to run the CLI. Detail: `references/debrief.md`.
 
-CLI missing → use the manual fallbacks inside each reference (still you write files; still never ask the FDE to run setup).
+CLI genuinely unavailable (no Node, offline, npx blocked) → use the manual fallbacks inside each reference (still you write files; still never ask the FDE to run setup). A skill-only install is not "unavailable": run the verb through `npx --yes fdeops …` so the gates, dating and redaction still hold.
 
 **Token model - where the cost goes.** Deterministic work is the CLI's job and costs **zero model tokens**: memory writes, recon, receipts, status, dashboard, and the bounded `fde resume`. Session-start hooks inject **TRIAGE + bounded `context.md` + a one-line pointer** - never this full skill body (that loads only when `@fde` triggers). Spend tokens only on judgment - reading the situation, routing, running the phase method, writing the artifact. Three rules keep a full day of FDE work cheap: load the router first and pull **one** reference only when you route to it; never dump a whole `.fde/` file into context - read the bounded resume, or `fde receipts <term>` for a targeted slice; don't re-read files you already have. The expensive model should fire for real decisions, not for plumbing the CLI already does.