fdeops 3.5.6 → 3.6.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (14) hide show
  1. package/README.md +97 -113
  2. package/adapters/AGENTS.md +1 -1
  3. package/adapters/GEMINI.md +1 -1
  4. package/adapters/copilot-instructions.md +1 -1
  5. package/adapters/cursor.fde.mdc +1 -1
  6. package/bin/check.js +13 -1
  7. package/bin/fde.js +234 -46
  8. package/bin/install.js +6 -0
  9. package/hooks/pre-compact +19 -0
  10. package/hooks/session-start +24 -3
  11. package/hooks/session-stop +23 -3
  12. package/package.json +1 -1
  13. package/skills/fde/SKILL.md +10 -9
  14. package/README.md.bak +0 -227
package/README.md CHANGED
@@ -1,176 +1,161 @@
1
- # FDEOps
1
+ # fdeops
2
2
 
3
- **The discipline and methodology for Forward Deployed Engineers.**
3
+ **Your AI coding agent forgets your client every morning. fdeops remembers.**
4
4
 
5
5
  [![npm version](https://img.shields.io/npm/v/fdeops)](https://www.npmjs.com/package/fdeops)
6
6
  [![CI](https://github.com/suboss87/fdeops/actions/workflows/validate.yml/badge.svg)](https://github.com/suboss87/fdeops/actions)
7
7
  [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
8
8
  [![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen)](https://nodejs.org)
9
9
 
10
- You embed at a client site. You bridge strategy and code. You ship on their systems, not yours.
10
+ Built for **Forward Deployed Engineers** - engineers embedded at a client, from first meeting to final handoff. Works the same for consultants, agency developers, solutions architects, and fractional CTOs.
11
11
 
12
- Every morning you open your AI coding agent, and it has no idea what happened yesterday with your projects/clients. You re-paste the same context. You explain the stakeholders again. You remind it about the scope change from Tuesday. Meanwhile, the real problem the one the brief didn't mention - sits undiscovered because nobody asked the right questions on day one.
12
+ ---
13
+
14
+ ## The problem
15
+
16
+ Your AI coding agent's memory is scoped to a **repo**. Client work isn't: one engagement spans several repos, a dozen stakeholders, and decisions made in meetings your agent never saw. That context lives in rooms, chats, and hallway conversations - nothing writes it down where your tools can use it.
13
17
 
14
- **fdeops fixes this.** One `@fde` command gives your AI coding agent a complete engagement methodology, a memory that writes itself, and a co-pilot that never assumes. Describe your situation, the agent confirms its understanding, generates specs where needed, and runs the right method from first stakeholder meeting, discovery workshops to final handoff. Tomorrow's session opens with a state summary and the one thing worth your attention.
18
+ fdeops adds the missing layer: memory scoped to the **client** - plain markdown at `~/fde-engagements/<client>/.fde/`, written as a side effect of doing the work. Local only, zero dependencies, no network, no telemetry.
19
+
20
+ ## Without fdeops vs with fdeops
21
+
22
+ | Moment | Without fdeops | With fdeops |
23
+ |---|---|---|
24
+ | **Monday morning** | Re-paste last week's context, re-explain the stakeholders | A hook loads the engagement at session start - the agent opens knowing the deadline and the open thread |
25
+ | **After a meeting** | Notes rot in a scratch file | `fde debrief` routes decisions, risks, deliveries, and contacts into the record, dated |
26
+ | **Scope dispute** | "Small" additions absorbed silently; no record when the sponsor asks | `fde receipts <term>` answers "when did we agree to that?" with dates |
27
+ | **Quiet stakeholder** | Noticed three weeks too late | `fde log contact --signal amber` the day it happens; `fde status` surfaces it |
28
+ | **Multiple clients** | Details blur across engagements | One folder per client, never cross-contaminated |
15
29
 
16
30
  ---
17
31
 
18
32
  ## Quickstart
19
33
 
20
- ### 1. Install
34
+ **1. Install** (Claude Code)
21
35
 
22
- **Claude Code**
23
- ```
36
+ ```text
24
37
  /plugin marketplace add suboss87/fdeops
25
38
  /plugin install fdeops@fdeops
26
39
  ```
27
40
 
28
- **Cursor · Codex · Copilot · Gemini CLI**
29
- ```bash
30
- npx fdeops adapters .
31
- ```
32
-
33
- **Local LLMs** - load `skills/fde/SKILL.md` as system prompt ([guide](adapters/LOCAL-LLM.md))
34
-
35
- ### 2. Create your first engagement
41
+ **2. Bind your client workspace** - run once, inside the workspace:
36
42
 
37
43
  ```bash
38
- npx fdeops init my-client # creates engagement memory
39
- export FDEOPS_ENGAGEMENT=~/fde-engagements/my-client/.fde # point your tool at it
44
+ fde resume --init acme
40
45
  ```
41
46
 
42
- Creates 12 markdown files at `~/fde-engagements/my-client/.fde/` - private to your machine, never uploaded.
47
+ fdeops' `--init` creates the engagement memory at `~/fde-engagements/acme/.fde/` (plain markdown, private to your machine) and binds this workspace to it. The hooks read that binding - context auto-loads at session start, auto-captures at session end. That is the whole setup.
43
48
 
44
- ### 3. Start working
49
+ **3. Work**
45
50
 
46
- ```
51
+ ```text
47
52
  @fde I just got the brief. New client, payments platform, 3-week timeline.
48
53
  ```
49
54
 
50
- Describe what's happening and the agent picks the right method. No configuration files to edit. No API keys. See [docs/USAGE.md](docs/USAGE.md) for the full workflow.
55
+ `@fde` is the one skill fdeops installs. Describe what's happening; it routes to the right field method and the memory writes itself. Full workflow: [docs/USAGE.md](docs/USAGE.md).
51
56
 
52
- > **Requires:** [Node.js](https://nodejs.org) >= 18 (for CLI and adapters). Claude Code plugin install does not require Node separately.
53
- >
54
- > **Other install methods:** `npx skills add suboss87/fdeops` (Skills CLI) or `git clone https://github.com/suboss87/fdeops.git && cd fdeops && node bin/install.js` (manual). Full install details: [docs/install.md](docs/install.md).
57
+ Not ready to install? `npx fdeops scan` runs on any repo you can read - day-1 recon (pure `git` + file reads, no config, no account) that maps hotspots, test gaps, and reverted attempts, and ends with the ASK ON DAY 1 questions the brief never mentions.
55
58
 
56
- ---
59
+ <details>
60
+ <summary><strong>Other install paths</strong> - Cursor, Codex, Copilot, Gemini CLI, local LLMs, air-gapped</summary>
57
61
 
58
- ## Who this is for
62
+ - **Cursor / Codex / Copilot / Gemini CLI:** `npx fdeops adapters .` drops a thin pointer to the same `@fde` skill - [adapters/](adapters/README.md)
63
+ - **Local LLMs (Ollama, LM Studio, llama.cpp):** load `skills/fde/SKILL.md` as the system prompt - [guide](adapters/LOCAL-LLM.md)
64
+ - **Skills CLI:** `npx skills add suboss87/fdeops`
65
+ - **Manual / air-gapped:** `git clone https://github.com/suboss87/fdeops.git && cd fdeops && node bin/install.js`
66
+ - **Requires:** [Node.js](https://nodejs.org) >= 18 for the CLI and adapters; the Claude Code plugin install does not need Node separately.
67
+ - **Advanced:** the `FDEOPS_ENGAGEMENT` env var overrides the workspace registry - only for unusual setups. Full matrix: [docs/install.md](docs/install.md)
59
68
 
60
- | You are... | What fdeops does for you |
61
- |----------|-------------------|
62
- | **Forward Deployed Engineer** | The role this was built for. 35 skills across the full engagement lifecycle - land, build, ship, close. |
63
- | **Consultant or contractor at a client site** | Every session, you re-explain context. fdeops remembers for you. |
64
- | **Solutions architect bridging strategy and code** | You navigate politics AND architecture. fdeops has methods for both. |
65
- | **Agency engineer running 3-5 clients** | Client details blur together. One `.fde/` per customer, never cross-contaminated. |
66
- | **Technical founder doing client work solo** | You ARE the team. The agent becomes your second brain. |
69
+ </details>
67
70
 
68
71
  ---
69
72
 
70
73
  ## How it works
71
74
 
72
- ```mermaid
73
- flowchart LR
74
- A["@fde"] --> B{"Describe\nyour situation"}
75
- B --> C["Embed & Trust"]
76
- B --> D["Discover & Diagnose"]
77
- B --> E["Plan & Align"]
78
- B --> F["Build & Guard"]
79
- B --> G["Ship & Verify"]
80
- B --> H["Operate & Close"]
81
- C --> I[".fde/ memory\n(written as you work)"]
82
- D --> I
83
- E --> I
84
- F --> I
85
- G --> I
86
- H --> I
87
- I --> J["Next session\nloads automatically"]
88
- ```
89
-
90
- 1. **Describe** your situation - "new client", "production is down", "need a board update", "red-team my handoff plan"
91
- 2. **Route** - the skill picks the right method from 35 options across 6 domains
92
- 3. **Confirm and execute** - the agent states its understanding, probes only where it elevates you, generates a spec before building, then runs the method and writes artifacts
93
- 4. **Compound** - next session opens with a state summary, flags what needs attention, and suggests the next move. Context never starts from zero again.
75
+ Two hooks and one router, on top of the fieldbook:
94
76
 
95
- <p align="center"><img width="794" height="571" alt="FieldBook" src="https://github.com/user-attachments/assets/349a223e-0c5e-4300-a8fe-9e3bb042cbbe" />
77
+ - **Session start** - a hook loads where you left off into your AI coding agent's context
78
+ - **Session end** - a hook captures what happened back into the fieldbook
79
+ - **After meetings** - `fde debrief notes.md` routes lines prefixed `decision:` / `risk:` / `delivery:` / `contact:` to the matching file, dated; everything else lands as a dated block in `context.md`
80
+ - **On top of the memory** - the `@fde` skill routes six phase verbs:
96
81
 
97
- Works with **Claude Code** - **Cursor** - **Copilot** - **Devin** - **Gemini CLI** - **Ollama** - **LM Studio** - any model that reads a markdown file
82
+ | Verb | When |
83
+ |------|------|
84
+ | **land** | First days at a new client - interrogate the brief, map stakeholders, define success |
85
+ | **discover** | The brief feels wrong - find the real problem, with evidence from the repo |
86
+ | **plan** | Scope agreed - sequence it backwards from success, in PR-sized slices |
87
+ | **build** | Ready to write code - declare blast radius, log deliveries as you ship |
88
+ | **ship** | Going to production - pre-flight, canary, tested rollback |
89
+ | **close** | Engagement ending - handoff doc, retrospective, receipts that survive you |
98
90
 
99
- ---
100
-
101
- ## Without fdeops vs with fdeops
102
-
103
- | | **Without fdeops** | **With fdeops** |
104
- |---|-------------------|----------------|
105
- | **Monday morning** | Re-paste last week's context, explain the stakeholders again | Agent opens with "last session you were on the ingest retry - CTO demo is Friday" |
106
- | **Scope creep** | Five "small" additions absorbed silently, timeline slips | Receipts timestamped - you walk into the sponsor meeting with evidence |
107
- | **Multiple customers** | Wrong client name in a status update, details blur | One folder per customer, context-switch protocol, cross-contamination checklist |
108
- | **The sponsor meeting** | "We completed the API endpoint" | "Manual reconciliation dropped from 3 FTEs to 0.5 - here's the rollback if it turns" |
109
- | **Before building** | AI builds what it thinks you meant, surprises in the PR | Agent generates the spec first, you approve in one word, zero surprises |
110
-
111
- ---
112
-
113
- ## 35 skills + 5 overlays
114
-
115
- | Domain | Skills | What it covers |
116
- |--------|--------|---------------|
117
- | **Embed & Trust** | land, audit, stakeholder-radar, trust-engineering, scope-defense | First days: access, credibility, scope |
118
- | **Discover & Diagnose** | discover, assumption-audit, use-case-scoring, sketch | Finding the real problem behind the brief |
119
- | **Plan & Align** | plan, business-case, options-analysis, initiative-triage | Sequencing work, getting sponsor alignment |
120
- | **Build & Guard** | build, incremental-build, test-on-legacy, blast-radius, debug, rescue, security-audit, observability | Building safely on their codebase |
121
- | **Ship & Verify** | ship, review, rollback-drill, qa-live | Getting to production without surprises |
122
- | **Operate & Close** | status, demo-prep, debrief, exec-narrative, dashboard, multi-customer-ops, close, handoff-engineering, pattern-extract, red-team | Running and ending the engagement well |
123
-
124
- **Overlays** activate automatically when your engagement involves AI projects, executive reporting, fintech, healthcare, or government compliance.
91
+ Overlays for regulated domains (AI, fintech, healthcare, government) activate on signal. fdeops complements your agent's native repo memory: CLAUDE.md holds how the *code* works; the fieldbook holds how the *engagement* works. Full matrix: [docs/skills.md](docs/skills.md).
125
92
 
126
- Full skill details: [docs/skills-reference.md](docs/skills-reference.md)
93
+ Works with **Claude Code** - **Cursor** - **Copilot** - **Devin** - **Gemini CLI** - **Ollama** - **LM Studio** - any model that reads a markdown file.
127
94
 
128
95
  ---
129
96
 
130
97
  ## Engagement memory (`.fde/`)
131
98
 
132
- Your **fieldbook** - one per client, private to you, plain markdown:
99
+ The **fieldbook** - one folder per client, plain markdown you can read, grep, and take with you:
133
100
 
134
- | File | Role | Written by |
135
- |------|------|-----------|
136
- | `context.md` | Where you are; loaded first every session | every phase + session-stop hook |
137
- | `brief.md` | What they said - hypothesis until discover | land |
138
- | `success.md` | Done, measured, signed-off by whom | land |
139
- | `reality.md` | The real problem, with evidence | discover / audit |
140
- | `terrain.md` | Codebase map: hotspots, test gaps, AI components, data estate | discover / audit |
141
- | `stakeholders.md` | Champions, resistance, trust signals | land, updated continuously |
142
- | `trust-profile.md` | Sacred data, AI policy, approval chain | land + overlays |
143
- | `decisions.md` | Plan + choices + integration contracts + sizing | plan / build / review / rescue |
144
- | `risks.md` | Live risk register | all phases |
145
- | `delivery.md` | What shipped, business value, rollback, pulse, adoption metrics | build / ship |
101
+ | File | Holds |
102
+ |------|-------|
103
+ | `context.md` | Where you are - loaded first every session |
104
+ | `brief.md` / `success.md` | What they asked for; what "done" means and who signs it off |
105
+ | `reality.md` / `terrain.md` | The real problem; the codebase map |
106
+ | `stakeholders.md` | Champions, resistance, `[signal:green\|amber\|red]` trust tokens |
107
+ | `trust-profile.md` | Sacred data, AI policy, approval chain |
108
+ | `decisions.md` / `risks.md` / `delivery.md` | Choices with dates; live risk register; what shipped and its rollback |
146
109
 
147
- Every claim is tagged with its source and date so you can defend it in front of skeptical stakeholders.
110
+ Every entry is dated and sourced, so you can defend it in front of skeptical stakeholders. Schema: [docs/schema.md](docs/schema.md).
148
111
 
149
112
  ---
150
113
 
151
114
  ## The CLI
152
115
 
153
- Your engagement toolkit - deterministic, offline, always available:
116
+ Deterministic, offline, zero tokens - the skill adds judgment on top:
154
117
 
155
118
  ```bash
156
- fde scan # day-1 recon: hotspots, test gaps, secrets, AI components
157
- fde resume # initialize or resume an engagement
158
- fde log # write decisions, risks, delivery, contacts
159
- fde receipts # search memory with dates - "what did we agree about X?"
160
- fde capture # session-end snapshot
161
- fde status # portfolio triage across all customers (red > amber > green)
162
- fde dashboard # render every engagement into one offline HTML fieldbook
119
+ fde scan # day-1 recon + ASK ON DAY 1 questions (works via npx)
120
+ fde resume # load this workspace's engagement
121
+ fde resume --init <client> # THE setup step: create + bind an engagement
122
+ fde debrief notes.md # route meeting notes into memory (also reads stdin)
123
+ fde log decision "descope agreed with Dana"
124
+ fde log contact "Diana gone quiet" --signal amber
125
+ fde receipts <term> # dated search; no hit = a gap in the record, not proof of absence
126
+ fde status # portfolio triage across all clients (red > amber > green)
127
+ fde dashboard # render every engagement into one offline HTML fieldbook
163
128
  ```
164
129
 
130
+ The latest dated `[signal:...]` token per stakeholder drives the trust column in `status` and `dashboard`; signals older than 21 days show as stale.
131
+
165
132
  <p align="center"><img src="media/terminal-demo.svg" alt="fde CLI - status, scan, dashboard" width="720"/></p>
166
133
 
134
+ <p align="center"><img width="794" height="571" alt="FieldBook" src="https://github.com/user-attachments/assets/349a223e-0c5e-4300-a8fe-9e3bb042cbbe" /></p>
135
+
136
+ ---
137
+
138
+ ## Who this is for
139
+
140
+ | You are... | What fdeops does for you |
141
+ |----------|-------------------|
142
+ | **Forward Deployed Engineer** | The role this was built for - the full lifecycle, first meeting to final handoff |
143
+ | **Consultant or contractor at a client site** | Remembers the engagement so you stop re-explaining it |
144
+ | **Solutions architect / engineer** | Methods for the politics as well as the architecture |
145
+ | **Agency developer running 3-5 clients** | One `.fde/` per client - details stop blurring |
146
+ | **Fractional CTO doing client work** | The fieldbook is your second brain - and your audit trail for billable work |
147
+
167
148
  ---
168
149
 
169
- ## Works with any AI coding tool
150
+ ## Your data stays yours
170
151
 
171
- One skill file powers every tool. Each adapter is a thin pointer at the same `@fde` skill - the methodology and memory stay consistent whether you use Claude Code, Codex, Cursor, Copilot, Gemini CLI, or a local model. Details: [`adapters/`](adapters/README.md).
152
+ - **Local only.** Pure `git` + file reads - no network calls, no telemetry, no account. Works air-gapped.
153
+ - **Plain markdown.** No database, no lock-in.
154
+ - **No new data path.** The AI sees client code only when *you* point your agent at it; `<private>`-tagged data never enters the model's context.
155
+ - **Nothing enters the record unreviewed.** The model drafts, you confirm (`fde debrief --dry-run` shows the routing first); the hooks record only git facts. Your fieldbook stays yours to defend.
156
+ - **Know your sync surface.** `~/fde-engagements` lives in your home directory - your backup and cloud-sync setup now covers client notes. `fde resume --init` warns if the folder sits in a synced path. Read [PRIVACY.md](PRIVACY.md) before your first NDA'd engagement.
172
157
 
173
- > **No cloud dependency.** fdeops calls no external API. The AI skill is a markdown file your model reads. The CLI is local Node.js. Works fully offline, fully air-gapped, fully private. See [`adapters/LOCAL-LLM.md`](adapters/LOCAL-LLM.md) for local model setup.
158
+ Details: [PRIVACY.md](PRIVACY.md) · [SECURITY.md](SECURITY.md)
174
159
 
175
160
  ---
176
161
 
@@ -180,7 +165,6 @@ One skill file powers every tool. Each adapter is a thin pointer at the same `@f
180
165
  - **Trust before production** - earn the right to touch their systems
181
166
  - **Brief is a hypothesis** - discover before building the wrong thing
182
167
  - **Evidence on every claim** - these files get defended in front of skeptical clients
183
- - **Map before moving** - unknown terrain gets characterisation tests
184
168
  - **Thin slices** - ship learning, not theatre
185
169
  - **One customer, one folder** - context never bleeds
186
170
 
@@ -196,6 +180,6 @@ cd fdeops && git pull && node bin/install.js
196
180
 
197
181
  ## Contributing
198
182
 
199
- Built and maintained by **[Subash Natarajan](https://www.linkedin.com/in/subashn/)**. Share your feedbacks via [Issues](https://github.com/suboss87/fdeops/issues) - see [CONTRIBUTING.md](CONTRIBUTING.md).
183
+ Built and maintained by **[Subash Natarajan](https://www.linkedin.com/in/subashn/)**. Share your feedback via [Issues](https://github.com/suboss87/fdeops/issues) - see [CONTRIBUTING.md](CONTRIBUTING.md).
200
184
 
201
- [FDE Methodology](FDE-METHODOLOGY.md) - [ATTRIBUTION.md](ATTRIBUTION.md) - [SECURITY.md](SECURITY.md) - [PRIVACY.md](PRIVACY.md) - [Repo layout](docs/REPO_LAYOUT.md) - [Skills reference](docs/skills-reference.md) - MIT
185
+ [FDE Methodology](FDE-METHODOLOGY.md) - [ATTRIBUTION.md](ATTRIBUTION.md) - [SECURITY.md](SECURITY.md) - [PRIVACY.md](PRIVACY.md) - [Repo layout](docs/REPO_LAYOUT.md) - [Skills matrix](docs/skills.md) - MIT
package/adapters/AGENTS.md CHANGED
@@ -11,7 +11,7 @@ When the FDE types **`@fde`** (or describes an engagement situation - new custom
11
11
 
12
12
  ## Engagement memory
13
13
 
14
- Read and write engagement files under **`FDEOPS_ENGAGEMENT`** (expand `~`). Default `~/fde-engagements/<name>/.fde/`. If unset, use `./.fde/` only when the engagement approves it and it is gitignored.
14
+ Read and write engagement files under the workspace's bound engagement: run `fde resume` to resolve it (binding created once with `fde resume --init <name>`; default `~/fde-engagements/<name>/.fde/`). `FDEOPS_ENGAGEMENT` (expand `~`) overrides when set. Use `./.fde/` only when the engagement approves it and it is gitignored.
15
15
 
16
16
  On entry, run `fde resume` (fallback `node ~/.claude/fdeops/fde.js resume`) to load `context.md`. Use the CLI for deterministic work - `fde scan | log | receipts | status | dashboard` - instead of improvising shell.
17
17
 
package/adapters/GEMINI.md CHANGED
@@ -11,7 +11,7 @@ When the FDE types **`@fde`** or describes an engagement situation (new customer
11
11
 
12
12
  ## Engagement memory
13
13
 
14
- Read and write engagement files under **`FDEOPS_ENGAGEMENT`** (expand `~`). Default `~/fde-engagements/<name>/.fde/`. If unset, use `./.fde/` only when the engagement approves it and it is gitignored.
14
+ Read and write engagement files under the workspace's bound engagement: run `fde resume` to resolve it (binding created once with `fde resume --init <name>`; default `~/fde-engagements/<name>/.fde/`). `FDEOPS_ENGAGEMENT` (expand `~`) overrides when set. Use `./.fde/` only when the engagement approves it and it is gitignored.
15
15
 
16
16
  On entry, run `fde resume` (fallback `node ~/.claude/fdeops/fde.js resume`) to load `context.md`. Use the CLI for deterministic work - `fde scan | log | receipts | status | dashboard` - instead of improvising shell.
17
17
 
package/adapters/copilot-instructions.md CHANGED
@@ -11,7 +11,7 @@ When the FDE types **`@fde`** or describes an engagement situation (new customer
11
11
 
12
12
  ## Engagement memory
13
13
 
14
- Read and write engagement files under **`FDEOPS_ENGAGEMENT`** (expand `~`). Default `~/fde-engagements/<name>/.fde/`. If unset, use `./.fde/` only when the engagement approves it and it is gitignored.
14
+ Read and write engagement files under the workspace's bound engagement: run `fde resume` to resolve it (binding created once with `fde resume --init <name>`; default `~/fde-engagements/<name>/.fde/`). `FDEOPS_ENGAGEMENT` (expand `~`) overrides when set. Use `./.fde/` only when the engagement approves it and it is gitignored.
15
15
 
16
16
  On entry, run `fde resume` (fallback `node ~/.claude/fdeops/fde.js resume`) to load `context.md`. Use the CLI for deterministic work - `fde scan | log | receipts | status | dashboard` - instead of improvising shell.
17
17
 
package/adapters/cursor.fde.mdc CHANGED
@@ -16,7 +16,7 @@ When the FDE types **`@fde`** or describes an engagement situation (new customer
16
16
 
17
17
  ## Engagement memory
18
18
 
19
- Read and write engagement files under **`FDEOPS_ENGAGEMENT`** (expand `~`). Default `~/fde-engagements/<name>/.fde/`. If unset, use `./.fde/` only when the engagement approves it and it is gitignored.
19
+ Read and write engagement files under the workspace's bound engagement: run `fde resume` to resolve it (binding created once with `fde resume --init <name>`; default `~/fde-engagements/<name>/.fde/`). `FDEOPS_ENGAGEMENT` (expand `~`) overrides when set. Use `./.fde/` only when the engagement approves it and it is gitignored.
20
20
 
21
21
  On entry, run `fde resume` (fallback `node ~/.claude/fdeops/fde.js resume`) to load `context.md`. Use the CLI for deterministic work - `fde scan | log | receipts | status | dashboard` - instead of improvising shell.
22
22
 
package/bin/check.js CHANGED
@@ -220,17 +220,29 @@ for (const h of ['session-start', 'session-stop', 'pre-compact']) {
220
220
  }
221
221
  ok('hook exec bits')
222
222
 
223
+ // registry-aware hooks: `fde resume --init` binds via ~/fde-engagements/.registry,
224
+ // so every hook must consult it or registry-bound users get zero auto-capture
225
+ for (const h of ['session-start', 'session-stop', 'pre-compact']) {
226
+ const body = read('hooks/' + h)
227
+ if (!body.includes('fde-engagements/.registry')) fail(`hooks/${h} must consult the workspace registry`)
228
+ if (!body.includes('registry_engagement_dir')) fail(`hooks/${h} missing registry_engagement_dir`)
229
+ }
230
+ ok('hooks registry-aware')
231
+
223
232
  // v3.1: the fde CLI (deterministic core)
224
233
  if (!fs.existsSync(path.join(root, 'bin', 'fde.js'))) {
225
234
  fail('bin/fde.js missing (the deterministic core)')
226
235
  } else {
227
236
  const cli = read('bin/fde.js')
228
- for (const sub of ['cmdScan', 'cmdResume', 'cmdLog', 'cmdReceipts', 'cmdCapture', 'cmdStatus']) {
237
+ for (const sub of ['cmdScan', 'cmdResume', 'cmdLog', 'cmdDebrief', 'cmdReceipts', 'cmdCapture', 'cmdStatus']) {
229
238
  if (!cli.includes(sub)) fail(`fde.js missing ${sub}`)
230
239
  }
231
240
  if (!JSON.parse(read('package.json')).bin.fde) fail('package.json must expose the fde bin')
232
241
  if (!read('bin/install.js').includes('fde.js')) fail('install.js must deploy fde.js')
233
242
  if (!read('skills/fde/SKILL.md').includes('fde resume')) fail('SKILL.md must use the CLI for memory ops')
243
+ if (!cli.includes('[signal:')) fail('fde.js must support structured [signal:x] trust tokens')
244
+ if (!cli.includes('ASK ON DAY 1')) fail('fde.js scan must emit ASK ON DAY 1 questions')
245
+ if (!read('bin/install.js').includes('FDE_SUBCOMMANDS')) fail('install.js must pass fde subcommands through (npx fdeops scan)')
234
246
  ok('fde CLI present and wired')
235
247
  }
236
248
  const hooksJson = JSON.parse(read('hooks/hooks.json'))