fdeops 3.13.0 → 3.15.1

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 (19) hide show
  1. package/AGENTS.md +1 -1
  2. package/README.md +182 -116
  3. package/adapters/LOCAL-LLM.md +1 -1
  4. package/adapters/README.md +2 -2
  5. package/bin/check.js +77 -48
  6. package/bin/fde.js +20 -11
  7. package/bin/lib/trust.js +3 -2
  8. package/mcp/fdeops-ingest/package.json +1 -1
  9. package/package.json +2 -2
  10. package/plugin.json +3 -3
  11. package/skills/fde/SKILL.md +78 -158
  12. package/skills/fde/references/pattern-extract.md +9 -9
  13. package/skills/fde/archive/sdlc/README.md +0 -7
  14. package/skills/fde/archive/sdlc/build.md +0 -154
  15. package/skills/fde/archive/sdlc/debug.md +0 -55
  16. package/skills/fde/archive/sdlc/observability.md +0 -103
  17. package/skills/fde/archive/sdlc/qa-live.md +0 -113
  18. package/skills/fde/archive/sdlc/security-audit.md +0 -105
  19. package/skills/fde/archive/sdlc/test-on-legacy.md +0 -108
package/AGENTS.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # AGENTS.md - working in the fdeops repository
2
2
 
3
- This repository **is** fdeops - the second brain for Forward Deployed Engineers. One `@fde` skill routes an entire client engagement across six domains, the `fde` CLI does the deterministic work, and per-customer memory lands in `.fde/` files as a side effect of the work (you still confirm judgment).
3
+ This repository **is** fdeops — the engagement record for Forward Deployed Engineers. One `@fde` skill, the `fde` CLI for deterministic work, and per-customer memory in `.fde/` as a side effect of the work (you still confirm judgment).
4
4
 
5
5
  ## If you are helping use fdeops in an engagement
6
6
 
package/README.md CHANGED
@@ -1,134 +1,238 @@
1
1
  # FDEOps
2
2
 
3
- **The AI coding agent forgets the client. fdeops is the countersigned record — promised, measured, accepted.**
3
+ **Forward deployed engineering skills for AI coding agents.**
4
4
 
5
- [![npm version](https://img.shields.io/npm/v/fdeops.svg)](https://www.npmjs.com/package/fdeops)
6
- [![CI](https://github.com/suboss87/fdeops/actions/workflows/validate.yml/badge.svg)](https://github.com/suboss87/fdeops/actions)
7
- [![skills.sh](https://skills.sh/b/suboss87/fdeops)](https://skills.sh/suboss87/fdeops)
8
- [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
9
- [![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen)](https://nodejs.org)
5
+ Skills encode the workflows, quality gates, and judgment Forward Deployed Engineers use on someone else's site. Packaged so an AI coding agent follows them consistently — and writes a dated record you can defend. The host agent still writes the TypeScript.
10
6
 
11
- One `@fde` skill. Four days on an embed:
7
+ ```text
8
+ LAND DISCOVER PLAN SHIP PROVE CLOSE
9
+ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐
10
+ │ Brief │ ───▶ │ Reality│ ───▶ │ Sequence│───▶ │ Live │ ───▶ │ Signed │ ───▶ │ They │
11
+ │ Trust │ │ Terrain│ │ Align │ │ slice │ │ off │ │ run │
12
+ └────────┘ └────────┘ └────────┘ └────────┘ └────────┘ └────────┘
13
+ /brief /discover /plan /ship /got /close
14
+ ```
12
15
 
13
- **the brief is wrong · they went quiet · when did we agree · what did they get**
16
+ ---
14
17
 
15
- The host agent still writes the TypeScript, runs the tests, and makes the commits. This skill is the engagement record. Do not ask `@fde` to review a unit test.
18
+ ## Commands
16
19
 
17
- Talk in plain language. The AI coding agent runs the plumbing. You confirm anything that enters the record.
20
+ 6 slash commands that map to the engagement. Each one activates `@fde`.
18
21
 
19
- ---
22
+ | What you're doing | Command | Key principle |
23
+ |-------------------|---------|-----------|
24
+ | Land the embed | `/brief` | Brief and trust before code |
25
+ | Find the real problem | `/discover` | Brief is a hypothesis |
26
+ | Plan the sequence | `/plan` | Backwards from done |
27
+ | Ship a slice | `/ship` | Pre-flight, then live |
28
+ | Prove what they got | `/got` | Promised → measured → accepted |
29
+ | Close the embed | `/close` | They can run it without you |
20
30
 
21
- ## The week
31
+ Also: `/debrief` (after a meeting) · `/prep` (walk-in) · `/quiet` (sponsor silent) · `/agreed` (scope dispute) · `/status` (Friday readout).
22
32
 
23
- `@fde` plus English. No cheat sheet.
33
+ Skills also activate automatically based on what you're doing — naming a client, debriefing a meeting, or asking what was agreed triggers `@fde`. Ordinary TypeScript, unit tests, and git commits stay in the host agent.
24
34
 
25
- | When | What you say | What you get |
26
- |------|--------------|--------------|
27
- | **The brief is wrong** | `@fde this is Acme. Brief says they want a portal.` | Real problem, or a gap. First chat: you name the client; the AI coding agent binds. |
28
- | **They went quiet** | `@fde the sponsor went quiet` | Trust signal in the record — process gap vs trust problem. |
29
- | **When did we agree?** | `@fde when did we agree to drop that?` | Dated receipts, or a clear gap. |
30
- | **What did they get?** | `@fde what did they get this week` | Friday ledger: promised → measured → accepted. |
31
- | **After a meeting** | `@fde` debrief these notes *(paste or attach)* | Proposed updates. You review, then confirm. |
32
- | **Optional: pull** | `@fde` connect Granola *(once)* · `@fde` pull today's Acme transcript | You add that source MCP. We **pull** on request — no push, no sync. [mcp/recipes/](mcp/recipes/) |
35
+ ---
33
36
 
34
- Same folder every time: `~/fde-engagements/<client>/.fde/`.
37
+ ## Quick Start
35
38
 
36
- **Words used here, once:** *engagement* - one client's body of work, one folder. *Fieldbook* - that folder (`.fde/`), the record itself. *Brief vs reality* - what they said the problem was, and what it turned out to be. *Terrain* - their systems and org as you actually found them. *Trust signal* - green / amber / red on one relationship. *Receipts* - the dated line proving something was agreed. *Vault* - the Obsidian copy `fde vault` generates to read it all in one window.
39
+ ```bash
40
+ npx skills add suboss87/fdeops --skill fde
41
+ ```
37
42
 
38
- ---
43
+ Then one chat. Name the client. The AI coding agent binds.
39
44
 
40
- ## Quickstart
45
+ ```text
46
+ @fde this is Acme
47
+ ```
41
48
 
42
- **1. Install** (30 seconds). Pick one — both copies `@fde` twice.
49
+ Paste kickoff notes in the same thread. `@fde` routes; you confirm judgment. Same folder every time: `~/fde-engagements/<client>/.fde/`. Workflow: [docs/USAGE.md](docs/USAGE.md).
43
50
 
44
- Claude Code (hooks before you type):
51
+ <details>
52
+ <summary><b>Claude Code (recommended)</b></summary>
45
53
 
46
54
  ```text
47
55
  /plugin marketplace add suboss87/fdeops
48
56
  /plugin install fdeops@fdeops
49
57
  ```
50
58
 
51
- Cursor, Codex, and any host that speaks the skills CLI:
59
+ Hooks load where you left off. Slash commands match the map above.
60
+
61
+ </details>
62
+
63
+ <details>
64
+ <summary><b>Cursor</b></summary>
52
65
 
53
66
  ```bash
54
67
  npx skills add suboss87/fdeops --skill fde
55
68
  ```
56
69
 
57
- **2. One chat.** Name the client. The AI coding agent binds the engagement; you never type the CLI.
70
+ Or `npx fdeops adapters .` — [adapters/](adapters/README.md).
58
71
 
59
- ```text
60
- @fde this is Acme
61
- ```
72
+ </details>
62
73
 
63
- Paste kickoff notes in the same thread. `@fde` routes; you confirm judgment. Workflow: [docs/USAGE.md](docs/USAGE.md).
74
+ <details>
75
+ <summary><b>Other agents</b></summary>
64
76
 
65
- Claude Code auto-loads the fieldbook at session start. Elsewhere, say `@fde`. Tomorrow the file is still there.
77
+ ```bash
78
+ npx skills add suboss87/fdeops --skill fde
79
+ ```
66
80
 
67
- <details>
68
- <summary>Terminal bind · other hosts · env</summary>
81
+ Gemini, Copilot, Codex, local LLMs: [adapters/](adapters/README.md). Air-gapped: `git clone https://github.com/suboss87/fdeops.git && node bin/install.js`.
69
82
 
70
- Fallback if the agent cannot bind — creates the engagement under `~/fde-engagements` and points this checkout at it:
83
+ Fallback if the agent cannot bind:
71
84
 
72
85
  ```bash
73
86
  npx fdeops resume --init acme # ~/fde-engagements/acme + bind this checkout
74
- npx fdeops resume # where we are
75
87
  ```
76
88
 
77
- - **Adapters** (Cursor rules, Gemini, Copilot): `npx fdeops adapters .` — [adapters/](adapters/README.md)
78
- - **Local LLMs:** load `skills/fde/SKILL.md` — [guide](adapters/LOCAL-LLM.md)
79
- - **Air-gapped:** `git clone https://github.com/suboss87/fdeops.git && cd fdeops && node bin/install.js`
80
- - **No install:** `npx fdeops demo` · `npx fdeops scan` (heuristic recon, not findings)
81
- - **Requires:** Node.js >= 18
82
- - **Override:** `FDEOPS_ENGAGEMENT` — [docs/install.md](docs/install.md)
89
+ Requires Node.js >= 18. Override: `FDEOPS_ENGAGEMENT` — [docs/install.md](docs/install.md). Try the loop: `npx fdeops demo`.
83
90
 
84
91
  </details>
85
92
 
86
93
  ---
87
94
 
88
- ## See it
95
+ ## All 31 Skills
89
96
 
90
- ```bash
91
- npx fdeops demo
97
+ The commands above are the entry points. Under the hood, `@fde` activates these 31 skills — each a structured workflow with steps, an artifact, and a checkpoint. You never pick one by name. Full detail: [docs/skills-reference.md](docs/skills-reference.md).
98
+
99
+ ### Land - Brief and trust
100
+
101
+ | Skill | What It Does | Use When |
102
+ |--------|--------------|----------|
103
+ | [land](skills/fde/references/land.md) | Interrogate the brief, map stakeholders, define success | New client, first meeting, just got the brief |
104
+ | [audit](skills/fde/references/audit.md) | Verify claims, find the load-bearing wall | Taking over, previous consultant left |
105
+ | [stakeholder-radar](skills/fde/references/stakeholder-radar.md) | Who decides, who blocks, who escalates | Need to know who matters |
106
+ | [trust-engineering](skills/fde/references/trust-engineering.md) | Observer → trusted; navigate AI policy | Need access or credibility |
107
+ | [scope-defense](skills/fde/references/scope-defense.md) | Scope receipts; the accumulation conversation | "Also can you…", timeline unchanged |
108
+
109
+ ### Discover - Find the real problem
110
+
111
+ | Skill | What It Does | Use When |
112
+ |--------|--------------|----------|
113
+ | [discover](skills/fde/references/discover.md) | Repo + workaround + the real problem | Brief feels wrong, shadow processes |
114
+ | [assumption-audit](skills/fde/references/assumption-audit.md) | Untested assumptions by blast radius | Brief feels too neat |
115
+ | [use-case-scoring](skills/fde/references/use-case-scoring.md) | Value × urgency × alignment / complexity | Everything is P0 |
116
+ | [sketch](skills/fde/references/sketch.md) | Kill the killer assumption in a day | Need to de-risk a direction |
117
+
118
+ ### Plan - Sequence the work
119
+
120
+ | Skill | What It Does | Use When |
121
+ |--------|--------------|----------|
122
+ | [plan](skills/fde/references/plan.md) | Backwards from done, PR-sized | What order, what is done |
123
+ | [business-case](skills/fde/references/business-case.md) | Cost of nothing → investment → return | Defend budget or timeline |
124
+ | [options-analysis](skills/fde/references/options-analysis.md) | Three genuine options | "What should we do?" |
125
+ | [initiative-triage](skills/fde/references/initiative-triage.md) | Pick three from twenty urgents | Everything is urgent |
126
+
127
+ ### Ship - Go live
128
+
129
+ | Skill | What It Does | Use When |
130
+ |--------|--------------|----------|
131
+ | [incremental-build](skills/fde/references/incremental-build.md) | Vertical slices, visible every 2–3 days | Large feature on their codebase |
132
+ | [blast-radius](skills/fde/references/blast-radius.md) | Impact from contained → irreversible | Touching shared infrastructure |
133
+ | [rescue](skills/fde/references/rescue.md) | Production fire or trust fire | Down, or they went quiet |
134
+ | [ship](skills/fde/references/ship.md) | Intent vs diff, pre-flight, rollback | Going live |
135
+ | [review](skills/fde/references/review.md) | Did we only build what we agreed | Before merge, scope creep |
136
+ | [rollback-drill](skills/fde/references/rollback-drill.md) | Test the escape route before 2am | "We can always revert" |
137
+
138
+ ### Prove - What they got
139
+
140
+ | Skill | What It Does | Use When |
141
+ |--------|--------------|----------|
142
+ | [status](skills/fde/references/status.md) | Promised → measured → accepted | Friday, sponsor update |
143
+ | [demo-prep](skills/fde/references/demo-prep.md) | One number, five hard questions | Demo or exec walkthrough |
144
+ | [debrief](skills/fde/references/debrief.md) | Meeting notes into the record | Just left a meeting |
145
+ | [exec-narrative](skills/fde/references/exec-narrative.md) | Board / sponsor's boss | Justify continued investment |
146
+ | [dashboard](skills/fde/references/dashboard.md) | Portfolio, trust-ordered | All my customers |
147
+ | [ingest](skills/fde/references/ingest.md) | Pull text you confirm | Transcript, Notion, Slack |
148
+ | [ingest-connect](skills/fde/references/ingest-connect.md) | Wire a source MCP | Connect Granola |
149
+
150
+ ### Close - They run it
151
+
152
+ | Skill | What It Does | Use When |
153
+ |--------|--------------|----------|
154
+ | [close](skills/fde/references/close.md) | Handoff that survives you | Wrapping up |
155
+ | [handoff-engineering](skills/fde/references/handoff-engineering.md) | Runbook, confidence scoring | They must operate without you |
156
+ | [multi-customer-ops](skills/fde/references/multi-customer-ops.md) | Switch without bleed | 2+ clients |
157
+ | [pattern-extract](skills/fde/references/pattern-extract.md) | If you did it twice, encode it | It will apply again |
158
+ | [red-team](skills/fde/references/red-team.md) | Stress-test before they do | "Poke holes in this" |
159
+
160
+ Overlays (on signal, not on request): [ai](skills/fde/references/ai.md) · [artifacts](skills/fde/references/artifacts.md) · [fintech](skills/fde/references/fintech.md) · [healthcare](skills/fde/references/healthcare.md) · [gov](skills/fde/references/gov.md) · [eval-pack](skills/fde/references/eval-pack.md)
161
+
162
+ Optional pull: you add the source MCP; we **pull** on request. [mcp/recipes/](mcp/recipes/)
163
+
164
+ ---
165
+
166
+ ## How Skills Work
167
+
168
+ Every skill follows a consistent anatomy:
169
+
170
+ ```
171
+ ┌─────────────────────────────────────────────┐
172
+ │ @fde (one skill) │
173
+ │ │
174
+ │ ┌─ Frontmatter ─────────────────────────┐ │
175
+ │ │ name: fde │ │
176
+ │ │ description: Use when [client work] │ │
177
+ │ └───────────────────────────────────────┘ │
178
+ │ │
179
+ │ Commands load it. English loads it. │
180
+ │ You confirm. Then .fde/ is written. │
181
+ └─────────────────────────────────────────────┘
182
+ │
183
+ ▼
184
+ references/<skill>.md fde CLI (local)
185
+ one file, then stop dating, gates, redaction
92
186
  ```
93
187
 
94
- Real commands on a fake client: messy notes → you confirm → cold reload → prep → receipts → fieldbook page. Nothing of yours is read. Lives in `~/fde-engagements/.demo/`. Remove with `npx fdeops demo --clean`.
188
+ - **Process, not prose.** Skills are workflows with an artifact and a checkpoint, not tip sheets.
189
+ - **You confirm.** Nothing is written until you say so.
190
+ - **Progressive disclosure.** The `SKILL.md` is the entry point. One `references/*.md` loads when routed.
191
+ - **Local CLI.** Writes, status, dated agreements. Zero model tokens. The AI coding agent runs it.
95
192
 
96
- One recorded session — kickoff notes, next morning, “when did we agree?” weeks later. CLI output; typing pace is staged. Re-record: [`media/record-session.sh`](media/record-session.sh).
193
+ The record lives at `~/fde-engagements/<client>/.fde/` — not inside any vendor. Change hosts, install `@fde` on the new one, bind if needed, keep talking.
97
194
 
98
- <p align="center"><img alt="A real fdeops session: messy kickoff notes routed into dated memory after you confirm, then a cold session that already knows the client, a grounded sponsor-meeting brief, and dated receipts" src="media/session.gif" width="900" /></p>
195
+ ---
99
196
 
100
- Two things a chat window cannot do: **nothing is written until you confirm**, and `<private>` lands sealed as `(private - redacted)` — never in `resume`, `prep`, `receipts`, or the dashboard.
197
+ ## Project Structure
198
+
199
+ ```
200
+ fdeops/
201
+ ├── skills/fde/ # the one skill
202
+ │ ├── SKILL.md # router
203
+ │ └── references/ # 31 skills + overlays
204
+ ├── .claude/commands/ # slash commands (each loads @fde)
205
+ ├── .claude-plugin/ # Claude Code marketplace
206
+ ├── bin/ # local CLI — git + files, no network
207
+ ├── hooks/ # session-start / session-stop / pre-compact
208
+ ├── adapters/ # Cursor, Gemini, Copilot, Codex pointers
209
+ ├── templates/.fde/ # memory files created on bind
210
+ ├── examples/ # fictional walkthroughs
211
+ ├── mcp/ # optional ingest + source recipes
212
+ ├── evals/ # routing checks + CLI attack notes
213
+ ├── media/ # recorded session (docs/USAGE.md)
214
+ └── docs/ # usage, schema, install, methodology
215
+ ```
101
216
 
102
217
  ---
103
218
 
104
- ## How it works
219
+ ## Why FDEOps?
105
220
 
106
- - **You** describe the situation with `@fde` (or plain language once the skill is loaded). First chat: you name the client; the AI coding agent runs the bind.
107
- - **Hooks (Claude Code)** load where you left off and snapshot on the way out. Other hosts: same CLI and files; you call `@fde`.
108
- - **Local CLI** — writes, receipts, status. Zero model tokens. The AI coding agent runs it; you do not live in the CLI. Friday, `fde status` prints promised → measured → accepted. [docs/USAGE.md](docs/USAGE.md)
109
- - **Pull (optional)** — FDEOps is the sink. Paste is the daily path. A source MCP you add (Granola, Slack, Notion, …) can fetch text; `@fde connect …` walks config. No push, no sync, no tokens in `.fde/`. [mcp/recipes/](mcp/recipes/)
221
+ ### 1. The brief is wrong
110
222
 
111
- `CLAUDE.md` is how the *code* works. The fieldbook is how the *engagement* works. The record lives at `~/fde-engagements/<client>/.fde/` — not inside any vendor.
223
+ The most common failure on an embed is building the portal they asked for. Ops has been running a spreadsheet for two years. `/brief` then `/discover` — who in their company would have to agree it worked?
112
224
 
113
- ### Switch coding agents anytime
225
+ ### 2. They went quiet
114
226
 
115
- Change hosts, install `@fde` on the new one, bind if needed, keep talking. The client record does not move.
227
+ A sponsor who stops answering is not a Jira gap. It is a trust color. `/quiet` — process vs trust, then a dated signal in the record.
116
228
 
117
- <details>
118
- <summary>Engagement verbs</summary>
229
+ ### 3. When did we agree?
119
230
 
120
- | Verb | When |
121
- |------|------|
122
- | **land** | First days — brief, stakeholders, success |
123
- | **discover** | The brief is wrong — evidence from the repo |
124
- | **plan** | Sequence backwards from done, PR-sized |
125
- | log delivery | After the host agent codes — what shipped, how it rolls back |
126
- | **ship** | Pre-flight, canary, rollback |
127
- | **close** | Handoff, retro, receipts that survive you |
231
+ Arguments from memory lose. `/agreed` searches dated receipts. No hit is a gap, not proof.
128
232
 
129
- Overlays (AI, fintech, healthcare, gov) fire on signal. [docs/skills.md](docs/skills.md)
233
+ ### 4. What did they get?
130
234
 
131
- </details>
235
+ A number only you agree with is claimed, not delivered. `/got` reads promised → measured → accepted out loud.
132
236
 
133
237
  ---
134
238
 
@@ -145,15 +249,7 @@ One folder per client. Plain markdown. Grep it, copy it, defend it.
145
249
  | `trust-profile.md` | Sacred data, AI policy, approval chain |
146
250
  | `decisions.md` / `risks.md` / `delivery.md` | Dated choices; live risks; what shipped and how it rolls back |
147
251
 
148
- Schema: [docs/schema.md](docs/schema.md).
149
-
150
- ---
151
-
152
- ## Fieldbook UI
153
-
154
- Local HTML: trust, phase, next, the record. `@fde` dashboard, or `npx fdeops dashboard` (`--all` for the portfolio).
155
-
156
- <p align="center"><img width="1336" height="624" alt="fdeops Fieldbook in the browser" src="https://github.com/user-attachments/assets/5683614c-7730-4a3a-860d-185053a377eb" /></p>
252
+ Schema: [docs/schema.md](docs/schema.md). Local HTML: `npx fdeops dashboard`.
157
253
 
158
254
  ---
159
255
 
@@ -161,23 +257,17 @@ Local HTML: trust, phase, next, the record. `@fde` dashboard, or `npx fdeops das
161
257
 
162
258
  | You are | What this is |
163
259
  |---------|----------------|
164
- | **Forward Deployed Engineer** | The job this was built for — first meeting through handoff |
260
+ | **Forward Deployed Engineer** | Client work that has to survive Monday morning |
165
261
  | **Consultant / contractor on site** | The engagement stops resetting every morning |
166
262
  | **Solutions architect** | Politics and architecture in the same record |
167
263
  | **Agency, 3–5 clients** | One `.fde/` each — they stop blurring |
168
264
  | **Fractional CTO on client work** | System of record for the embed, and the billable trail |
169
265
 
170
- Ordinary TypeScript, unit tests, and git commits stay in the host agent.
171
-
172
266
  ---
173
267
 
174
268
  ## Your data stays yours
175
269
 
176
- - **Local only.** `git` + files. No network, no telemetry, no account. Air-gapped is fine.
177
- - **Plain markdown.** No database.
178
- - **No new data path.** The model sees client code only when you point the AI coding agent at it. `<private>` is redacted from CLI, dashboard, and hooks — do not open raw private blocks with file tools.
179
- - **Nothing unreviewed.** Draft → you confirm. `fde debrief --dry-run` shows routing first.
180
- - **Know the sync surface.** `~/fde-engagements` is in `$HOME`. iCloud/Dropbox is an NDA incident waiting. `resume --init` warns. [PRIVACY.md](PRIVACY.md) before the first NDA.
270
+ Local only — `git` + files, no network, no telemetry. Plain markdown. The model sees client code only when you point the AI coding agent at it. `<private>` is redacted from CLI, dashboard, and hooks. Nothing is written until you confirm. `~/fde-engagements` is in `$HOME`; iCloud/Dropbox is an NDA incident waiting.
181
271
 
182
272
  [PRIVACY.md](PRIVACY.md) · [SECURITY.md](SECURITY.md)
183
273
 
@@ -186,43 +276,19 @@ Ordinary TypeScript, unit tests, and git commits stay in the host agent.
186
276
  ## Principles
187
277
 
188
278
  - **The artifact is the memory** — producing the work and recording it are one action
189
- - **Methods, not autonomy** — the kit says what to check; judgment stays yours
279
+ - **Skills, not autonomy** — the kit says what to check; judgment stays yours
190
280
  - **Brief is a hypothesis** — discover before building the wrong thing
191
281
  - **Evidence on every claim** — these files get defended in the room
192
282
  - **One customer, one folder** — context never bleeds
193
283
 
194
284
  ---
195
285
 
196
- ## Updating
197
-
198
- Re-run the Quickstart install, or from a clone: `git pull && node bin/install.js`
199
-
200
- ---
201
-
202
286
  ## Contributing
203
287
 
204
288
  **[Subash Natarajan](https://www.linkedin.com/in/subashn/)**. [Issues](https://github.com/suboss87/fdeops/issues) · [CONTRIBUTING.md](CONTRIBUTING.md)
205
289
 
206
- **What we won't build:** SaaS sync; Slack/Notion/Granola connectors or **push** inside the CLI; CRM as core; hardware capture; generic code-craft packs. You may **pull** via *your* MCP. The `fde` CLI stays local-only.
290
+ Skills should be **specific** (actionable steps), **verifiable** (an artifact in `.fde/`), and **minimal**. The `fde` CLI stays local-only.
207
291
 
208
- [FDE Methodology](FDE-METHODOLOGY.md) · [SECURITY.md](SECURITY.md) · [PRIVACY.md](PRIVACY.md) · [Repo layout](docs/REPO_LAYOUT.md) · [Skills matrix](docs/skills.md) · MIT
292
+ ## License
209
293
 
210
- ---
211
-
212
- <details>
213
- <summary>31 field methods (you never pick one)</summary>
214
-
215
- You describe the situation; `@fde` routes. **31 methods**, six domains — each a method (thinking, artifact, checkpoint), not a tip sheet. [docs/skills.md](docs/skills.md) · [docs/skills-reference.md](docs/skills-reference.md)
216
-
217
- | Domain | Methods |
218
- |--------|---------|
219
- | **1. Embed & Trust** | [land](skills/fde/references/land.md) · [audit](skills/fde/references/audit.md) · [stakeholder-radar](skills/fde/references/stakeholder-radar.md) · [trust-engineering](skills/fde/references/trust-engineering.md) · [scope-defense](skills/fde/references/scope-defense.md) |
220
- | **2. Discover & Diagnose** | [discover](skills/fde/references/discover.md) · [assumption-audit](skills/fde/references/assumption-audit.md) · [use-case-scoring](skills/fde/references/use-case-scoring.md) · [sketch](skills/fde/references/sketch.md) |
221
- | **3. Plan & Align** | [plan](skills/fde/references/plan.md) · [business-case](skills/fde/references/business-case.md) · [options-analysis](skills/fde/references/options-analysis.md) · [initiative-triage](skills/fde/references/initiative-triage.md) |
222
- | **4. Build & Guard** | [incremental-build](skills/fde/references/incremental-build.md) · [blast-radius](skills/fde/references/blast-radius.md) · [rescue](skills/fde/references/rescue.md) |
223
- | **5. Ship & Verify** | [ship](skills/fde/references/ship.md) · [review](skills/fde/references/review.md) · [rollback-drill](skills/fde/references/rollback-drill.md) |
224
- | **6. Operate & Close** | [status](skills/fde/references/status.md) · [demo-prep](skills/fde/references/demo-prep.md) · [debrief](skills/fde/references/debrief.md) · [exec-narrative](skills/fde/references/exec-narrative.md) · [dashboard](skills/fde/references/dashboard.md) · [multi-customer-ops](skills/fde/references/multi-customer-ops.md) · [close](skills/fde/references/close.md) · [handoff-engineering](skills/fde/references/handoff-engineering.md) · [pattern-extract](skills/fde/references/pattern-extract.md) · [red-team](skills/fde/references/red-team.md) · [ingest](skills/fde/references/ingest.md) · [ingest-connect](skills/fde/references/ingest-connect.md) |
225
-
226
- Overlays: [ai](skills/fde/references/ai.md) · [artifacts](skills/fde/references/artifacts.md) · [fintech](skills/fde/references/fintech.md) · [healthcare](skills/fde/references/healthcare.md) · [gov](skills/fde/references/gov.md)
227
-
228
- </details>
294
+ MIT — use these skills on client work.
package/adapters/LOCAL-LLM.md CHANGED
@@ -62,7 +62,7 @@ The model reads SKILL.md, routes to the right skill, and produces artifacts in y
62
62
 
63
63
  ## Model size recommendations
64
64
 
65
- The methodology is detailed (31 methods, routing logic, evidence format, memory contract). Larger models handle it better:
65
+ The methodology is detailed (31 skills, routing logic, evidence format, memory contract). Larger models handle it better:
66
66
 
67
67
  | Model class | Experience |
68
68
  |-------------|-----------|
package/adapters/README.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  **One brain, thin adapters.** fdeops has a single source of truth - the `@fde` skill at `skills/fde/SKILL.md` and the `fde` CLI. Each AI coding tool discovers it through a small pointer file in the place that tool already looks. No forked logic, no five copies to maintain - every adapter says the same thing: *route via `@fde`, read/write `.fde/` memory, talk like a peer, never touch what isn't yours.*
4
4
 
5
- **Switching tools:** the fieldbook does not live in the agent. It lives at `~/fde-engagements/<client>/.fde/`. Point a new tool at a bound workspace, drop adapters (or install the skill/plugin for that tool), and the same client record opens. Auto session hooks are Claude Code–first; elsewhere load via `@fde` / `fde resume`. See [README § Switch coding agents](../README.md#switch-coding-agents-anytime).
5
+ **Switching tools:** the fieldbook does not live in the agent. It lives at `~/fde-engagements/<client>/.fde/`. Point a new tool at a bound workspace, drop adapters (or install the skill/plugin for that tool), and the same client record opens. Auto session hooks are Claude Code–first; elsewhere load via `@fde` / `fde resume`. See [README § How it works](../README.md#how-it-works).
6
6
 
7
7
  ## What goes where
8
8
 
@@ -31,4 +31,4 @@ Defaults to the current directory if no path is given. Existing files are never
31
31
 
32
32
  ## The principle
33
33
 
34
- The adapter only tells the tool **where the brain is and how to behave**. All the method - the 31 methods, the overlays, the memory contract - lives once in `skills/fde/SKILL.md`. Update the brain, every platform gets it. That's why fdeops feels native in whatever the FDE already uses, without five things to keep in sync.
34
+ The adapter only tells the tool **where the brain is and how to behave**. All 31 skills, the overlays, and the memory contract live once in `skills/fde/SKILL.md`. Update the brain, every platform gets it. That's why fdeops feels native in whatever the FDE already uses, without five things to keep in sync.