fdeops 3.15.1 → 3.16.0

package/AGENTS.md

@@ -1,6 +1,6 @@
 # AGENTS.md - working in the fdeops repository
 
-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).
+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).
 
 ## If you are helping use fdeops in an engagement
 

package/README.md

@@ -2,7 +2,7 @@
 
 **Forward deployed engineering skills for AI coding agents.**
 
-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.
+Skills encode the workflows, quality gates, and judgment Forward Deployed Engineers use on someone else's site. Packaged so an AI coding agent can run the embed end-to-end: discovery, POC, slice, on-site proof, eval, signed outcome. The workspace still compiles and commits. `@fde` does not leave.
 
 ```text
   LAND              DISCOVER           PLAN              SHIP               PROVE              CLOSE
@@ -10,27 +10,35 @@ Skills encode the workflows, quality gates, and judgment Forward Deployed Engine
  │  Brief │ ───▶ │ Reality│ ───▶ │ Sequence│───▶ │  Live  │ ───▶ │ Signed │ ───▶ │  They  │
  │  Trust │      │ Terrain│      │  Align │      │  slice │      │   off  │      │   run  │
  └────────┘      └────────┘      └────────┘      └────────┘      └────────┘      └────────┘
-  /brief           /discover          /plan             /ship              /got              /close
+  /brief           /discover          /plan             /ship            /outcome           /close
 ```
 
 ---
 
 ## Commands
 
-6 slash commands that map to the engagement. Each one activates `@fde`.
+Each command loads the same `@fde` skill. You never pick from 31 names.
 
 | What you're doing | Command | Key principle |
 |-------------------|---------|-----------|
-| Land the embed | `/brief` | Brief and trust before code |
+| Land the embed | `/brief` | Who signs done |
 | Find the real problem | `/discover` | Brief is a hypothesis |
 | Plan the sequence | `/plan` | Backwards from done |
-| Ship a slice | `/ship` | Pre-flight, then live |
-| Prove what they got | `/got` | Promised → measured → accepted |
-| Close the embed | `/close` | They can run it without you |
+| Ship a slice | `/ship` | Live with a rollback |
+| Prove the outcome | `/outcome` | Promised, measured, accepted |
+| Close the embed | `/close` | They run it without you |
 
-Also: `/debrief` (after a meeting) · `/prep` (walk-in) · `/quiet` (sponsor silent) · `/agreed` (scope dispute) · `/status` (Friday readout).
+Also:
 
-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.
+| What you're doing | Command | Key principle |
+|-------------------|---------|-----------|
+| Sponsor went silent | `/trust` | Process or trust |
+| Scope dispute | `/receipts` | Dated, or a gap |
+| After a meeting | `/debrief` | Notes into the record |
+| Walk-in | `/prep` | One page from the record |
+| Friday readout | `/readout` | Promised, measured, accepted |
+
+Skills also activate on English: naming a client, running a POC, slicing a feature, asking what was agreed. A throwaway one-liner in an unbound repo can skip `@fde`. A client slice cannot.
 
 ---
 
@@ -67,7 +75,7 @@ Hooks load where you left off. Slash commands match the map above.
 npx skills add suboss87/fdeops --skill fde
 ```
 
-Or `npx fdeops adapters .` — [adapters/](adapters/README.md).
+Or `npx fdeops adapters .`. See [adapters/](adapters/README.md).
 
 </details>
 
@@ -86,7 +94,7 @@ Fallback if the agent cannot bind:
 npx fdeops resume --init acme   # ~/fde-engagements/acme + bind this checkout
 ```
 
-Requires Node.js >= 18. Override: `FDEOPS_ENGAGEMENT` — [docs/install.md](docs/install.md). Try the loop: `npx fdeops demo`.
+Requires Node.js >= 18. Override: `FDEOPS_ENGAGEMENT`. See [docs/install.md](docs/install.md). Try the loop: `npx fdeops demo`.
 
 </details>
 
@@ -94,7 +102,7 @@ Requires Node.js >= 18. Override: `FDEOPS_ENGAGEMENT` — [docs/install.md](docs
 
 ## All 31 Skills
 
-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).
+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).
 
 ### Land - Brief and trust
 
@@ -102,18 +110,18 @@ The commands above are the entry points. Under the hood, `@fde` activates these
 |--------|--------------|----------|
 | [land](skills/fde/references/land.md) | Interrogate the brief, map stakeholders, define success | New client, first meeting, just got the brief |
 | [audit](skills/fde/references/audit.md) | Verify claims, find the load-bearing wall | Taking over, previous consultant left |
-| [stakeholder-radar](skills/fde/references/stakeholder-radar.md) | Who decides, who blocks, who escalates | Need to know who matters |
-| [trust-engineering](skills/fde/references/trust-engineering.md) | Observer → trusted; navigate AI policy | Need access or credibility |
-| [scope-defense](skills/fde/references/scope-defense.md) | Scope receipts; the accumulation conversation | "Also can you…", timeline unchanged |
+| [who-decides](skills/fde/references/who-decides.md) | Who decides, who blocks, who escalates | Need to know who matters |
+| [earn-trust](skills/fde/references/earn-trust.md) | Observer → trusted; navigate AI policy | Need access or credibility |
+| [hold-scope](skills/fde/references/hold-scope.md) | Scope receipts; the accumulation conversation | "Also can you…", timeline unchanged |
 
 ### Discover - Find the real problem
 
 | Skill | What It Does | Use When |
 |--------|--------------|----------|
 | [discover](skills/fde/references/discover.md) | Repo + workaround + the real problem | Brief feels wrong, shadow processes |
-| [assumption-audit](skills/fde/references/assumption-audit.md) | Untested assumptions by blast radius | Brief feels too neat |
-| [use-case-scoring](skills/fde/references/use-case-scoring.md) | Value × urgency × alignment / complexity | Everything is P0 |
-| [sketch](skills/fde/references/sketch.md) | Kill the killer assumption in a day | Need to de-risk a direction |
+| [test-assumptions](skills/fde/references/test-assumptions.md) | Untested assumptions by blast radius | Brief feels too neat |
+| [score-use-cases](skills/fde/references/score-use-cases.md) | Value × urgency × alignment / complexity | Everything is P0 |
+| [poc](skills/fde/references/poc.md) | Kill the killer assumption in a day | POC, spike, need to de-risk |
 
 ### Plan - Sequence the work
 
@@ -121,40 +129,40 @@ The commands above are the entry points. Under the hood, `@fde` activates these
 |--------|--------------|----------|
 | [plan](skills/fde/references/plan.md) | Backwards from done, PR-sized | What order, what is done |
 | [business-case](skills/fde/references/business-case.md) | Cost of nothing → investment → return | Defend budget or timeline |
-| [options-analysis](skills/fde/references/options-analysis.md) | Three genuine options | "What should we do?" |
-| [initiative-triage](skills/fde/references/initiative-triage.md) | Pick three from twenty urgents | Everything is urgent |
+| [three-options](skills/fde/references/three-options.md) | Three genuine options | "What should we do?" |
+| [pick-three](skills/fde/references/pick-three.md) | Pick three from twenty urgents | Everything is urgent |
 
 ### Ship - Go live
 
 | Skill | What It Does | Use When |
 |--------|--------------|----------|
-| [incremental-build](skills/fde/references/incremental-build.md) | Vertical slices, visible every 2–3 days | Large feature on their codebase |
-| [blast-radius](skills/fde/references/blast-radius.md) | Impact from contained → irreversible | Touching shared infrastructure |
+| [thin-slices](skills/fde/references/thin-slices.md) | Vertical slices, on-site proof | Building on their codebase |
+| [what-breaks](skills/fde/references/what-breaks.md) | Impact from contained → irreversible | Touching shared infrastructure |
 | [rescue](skills/fde/references/rescue.md) | Production fire or trust fire | Down, or they went quiet |
 | [ship](skills/fde/references/ship.md) | Intent vs diff, pre-flight, rollback | Going live |
 | [review](skills/fde/references/review.md) | Did we only build what we agreed | Before merge, scope creep |
-| [rollback-drill](skills/fde/references/rollback-drill.md) | Test the escape route before 2am | "We can always revert" |
+| [rollback](skills/fde/references/rollback.md) | Test the escape route before 2am | "We can always revert" |
 
-### Prove - What they got
+### Prove - Outcome
 
 | Skill | What It Does | Use When |
 |--------|--------------|----------|
-| [status](skills/fde/references/status.md) | Promised → measured → accepted | Friday, sponsor update |
+| [readout](skills/fde/references/readout.md) | Promised → measured → accepted | Friday, sponsor update |
 | [demo-prep](skills/fde/references/demo-prep.md) | One number, five hard questions | Demo or exec walkthrough |
 | [debrief](skills/fde/references/debrief.md) | Meeting notes into the record | Just left a meeting |
-| [exec-narrative](skills/fde/references/exec-narrative.md) | Board / sponsor's boss | Justify continued investment |
+| [board-memo](skills/fde/references/board-memo.md) | Board / sponsor's boss | Justify continued investment |
 | [dashboard](skills/fde/references/dashboard.md) | Portfolio, trust-ordered | All my customers |
 | [ingest](skills/fde/references/ingest.md) | Pull text you confirm | Transcript, Notion, Slack |
-| [ingest-connect](skills/fde/references/ingest-connect.md) | Wire a source MCP | Connect Granola |
+| [connect](skills/fde/references/connect.md) | Wire a source MCP | Connect Granola |
 
 ### Close - They run it
 
 | Skill | What It Does | Use When |
 |--------|--------------|----------|
 | [close](skills/fde/references/close.md) | Handoff that survives you | Wrapping up |
-| [handoff-engineering](skills/fde/references/handoff-engineering.md) | Runbook, confidence scoring | They must operate without you |
-| [multi-customer-ops](skills/fde/references/multi-customer-ops.md) | Switch without bleed | 2+ clients |
-| [pattern-extract](skills/fde/references/pattern-extract.md) | If you did it twice, encode it | It will apply again |
+| [runbook](skills/fde/references/runbook.md) | Runbook, confidence scoring | They must operate without you |
+| [switch-clients](skills/fde/references/switch-clients.md) | Switch without bleed | 2+ clients |
+| [encode-pattern](skills/fde/references/encode-pattern.md) | If you did it twice, encode it | It will apply again |
 | [red-team](skills/fde/references/red-team.md) | Stress-test before they do | "Poke holes in this" |
 
 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)
@@ -165,32 +173,31 @@ Optional pull: you add the source MCP; we **pull** on request. [mcp/recipes/](mc
 
 ## How Skills Work
 
-Every skill follows a consistent anatomy:
+One skill. One reference file per situation. One folder per client.
 
 ```
-┌─────────────────────────────────────────────┐
-│  @fde  (one skill)                          │
-│                                             │
-│  ┌─ Frontmatter ─────────────────────────┐  │
-│  │ name: fde                             │  │
-│  │ description: Use when [client work]   │  │
-│  └───────────────────────────────────────┘  │
-│                                             │
-│  Commands load it. English loads it.        │
-│  You confirm. Then .fde/ is written.        │
-└─────────────────────────────────────────────┘
-         │
-         ▼
-  references/<skill>.md      fde CLI (local)
-  one file, then stop        dating, gates, redaction
+  /brief   or   "@fde this is Acme"
+           │
+           ▼
+  skills/fde/SKILL.md          hosts load this one file
+           │  routes. you never pick a skill by name
+           ▼
+  references/land.md           one workflow, then stop
+           │
+           ▼
+  fde CLI (local)              dates, gates, redacts. no network
+           │  after you confirm
+           ▼
+  ~/fde-engagements/<client>/.fde/
 ```
 
-- **Process, not prose.** Skills are workflows with an artifact and a checkpoint, not tip sheets.
+- **Process, not prose.** Each reference is a workflow with an artifact and a checkpoint, not a tip sheet.
+- **Ground loop.** Name → characterise → prove where they live → log. The workspace compiles; `@fde` stays.
 - **You confirm.** Nothing is written until you say so.
-- **Progressive disclosure.** The `SKILL.md` is the entry point. One `references/*.md` loads when routed.
-- **Local CLI.** Writes, status, dated agreements. Zero model tokens. The AI coding agent runs it.
+- **Progressive disclosure.** `SKILL.md` is the entry point. One `references/*.md` loads when routed.
+- **Local CLI.** Writes and status cost zero model tokens. The AI coding agent runs it.
 
-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.
+Change hosts, install `@fde` on the new one, bind if needed, keep talking. The record is not inside any vendor.
 
 ---
 
@@ -198,41 +205,76 @@ The record lives at `~/fde-engagements/<client>/.fde/` — not inside any vendor
 
 ```
 fdeops/
-├── skills/fde/                 # the one skill
-│   ├── SKILL.md                #   router
-│   └── references/             #   31 skills + overlays
-├── .claude/commands/           # slash commands (each loads @fde)
-├── .claude-plugin/             # Claude Code marketplace
-├── bin/                        # local CLI — git + files, no network
-├── hooks/                      # session-start / session-stop / pre-compact
-├── adapters/                   # Cursor, Gemini, Copilot, Codex pointers
-├── templates/.fde/             # memory files created on bind
-├── examples/                   # fictional walkthroughs
-├── mcp/                        # optional ingest + source recipes
-├── evals/                      # routing checks + CLI attack notes
-├── media/                      # recorded session (docs/USAGE.md)
-└── docs/                       # usage, schema, install, methodology
+├── skills/fde/                            # the one skill hosts load
+│   ├── SKILL.md                           #   router
+│   └── references/                        #   31 skills + overlays (you never pick)
+│       ├── land.md                        #   Land
+│       ├── audit.md
+│       ├── who-decides.md
+│       ├── earn-trust.md
+│       ├── hold-scope.md
+│       ├── discover.md                    #   Discover
+│       ├── test-assumptions.md
+│       ├── score-use-cases.md
+│       ├── poc.md
+│       ├── plan.md                        #   Plan
+│       ├── business-case.md
+│       ├── three-options.md
+│       ├── pick-three.md
+│       ├── thin-slices.md                 #   Ship
+│       ├── what-breaks.md
+│       ├── rescue.md
+│       ├── ship.md
+│       ├── review.md
+│       ├── rollback.md
+│       ├── readout.md                      #   Prove
+│       ├── demo-prep.md
+│       ├── debrief.md
+│       ├── board-memo.md
+│       ├── dashboard.md
+│       ├── ingest.md
+│       ├── connect.md
+│       ├── close.md                       #   Close
+│       ├── runbook.md
+│       ├── switch-clients.md
+│       ├── encode-pattern.md
+│       ├── red-team.md
+│       ├── ai.md                          #   overlays (on signal)
+│       ├── artifacts.md
+│       ├── eval-pack.md
+│       ├── fintech.md
+│       ├── healthcare.md
+│       └── gov.md
+├── .claude/commands/                      # slash commands (each loads @fde)
+│   ├── brief.md
+│   ├── discover.md
+│   ├── plan.md
+│   ├── ship.md
+│   ├── outcome.md
+│   ├── close.md
+│   ├── trust.md
+│   ├── receipts.md
+│   ├── debrief.md
+│   ├── prep.md
+│   └── readout.md
+├── .claude-plugin/                        # Claude Code marketplace
+├── bin/                                   # local CLI: git + files, no network
+├── hooks/                                 # session-start / session-stop / pre-compact
+├── adapters/                              # Cursor, Gemini, Copilot, Codex pointers
+├── templates/.fde/                        # memory files created on bind
+├── examples/                              # fictional walkthroughs
+├── mcp/                                   # optional ingest + source recipes
+├── evals/                                 # routing checks
+└── docs/                                  # usage, schema, install
 ```
 
 ---
 
 ## Why FDEOps?
 
-### 1. The brief is wrong
-
-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?
-
-### 2. They went quiet
+AI coding agents are built for a repo, not for a client. They forget the sponsor, the promise, who can say yes, and whether anyone accepted the number. Monday morning they start from the ticket again.
 
-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.
-
-### 3. When did we agree?
-
-Arguments from memory lose. `/agreed` searches dated receipts. No hit is a gap, not proof.
-
-### 4. What did they get?
-
-A number only you agree with is claimed, not delivered. `/got` reads promised → measured → accepted out loud.
+FDEOps is what you take on site. One `@fde` skill runs the embed from discovery to signed outcome: POC, slice, on-site proof, eval when a model judges, promised → measured → accepted. A local CLI dates every decision. `.fde/` is markdown on your laptop. You confirm; then it is on the record.
 
 ---
 
@@ -255,19 +297,15 @@ Schema: [docs/schema.md](docs/schema.md). Local HTML: `npx fdeops dashboard`.
 
 ## Who this is for
 
-| You are | What this is |
-|---------|----------------|
-| **Forward Deployed Engineer** | Client work that has to survive Monday morning |
-| **Consultant / contractor on site** | The engagement stops resetting every morning |
-| **Solutions architect** | Politics and architecture in the same record |
-| **Agency, 3–5 clients** | One `.fde/` each — they stop blurring |
-| **Fractional CTO on client work** | System of record for the embed, and the billable trail |
+You embed with a customer and an AI coding agent. Take this on the ground. Discovery through signed outcome lives in `@fde`. One `.fde/` per client so they do not blur.
+
+If you only write code in your own repo with no client record to defend, you do not need this kit.
 
 ---
 
 ## Your data stays yours
 
-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 `$HOME`; iCloud/Dropbox is an NDA incident waiting.
+Local only - `git` + files, no network, no telemetry. Plain markdown. The model sees client code only when you point the AI coding agent at it. `<private>` is redacted from CLI, dashboard, and hooks. Nothing is written until you confirm. `~/fde-engagements` is in `$HOME`; iCloud/Dropbox is an NDA incident waiting.
 
 [PRIVACY.md](PRIVACY.md) · [SECURITY.md](SECURITY.md)
 
@@ -275,20 +313,21 @@ Local only — `git` + files, no network, no telemetry. Plain markdown. The mode
 
 ## Principles
 
-- **The artifact is the memory** — producing the work and recording it are one action
-- **Skills, not autonomy** — the kit says what to check; judgment stays yours
-- **Brief is a hypothesis** — discover before building the wrong thing
-- **Evidence on every claim** — these files get defended in the room
-- **One customer, one folder** — context never bleeds
+- **The artifact is the memory** - producing the work and recording it are one action
+- **Ground loop** - name the slice, characterise their code, prove it where they live, log the outcome
+- **Skills, not autonomy** - the kit says what to check; judgment stays yours
+- **Brief is a hypothesis** - discover before building the wrong thing
+- **Evidence on every claim** - these files get defended in the room
+- **One customer, one folder** - context never bleeds
 
 ---
 
 ## Contributing
 
-**[Subash Natarajan](https://www.linkedin.com/in/subashn/)**. [Issues](https://github.com/suboss87/fdeops/issues) · [CONTRIBUTING.md](CONTRIBUTING.md)
+**[Subash Natarajan](https://www.linkedin.com/in/subashn/)**. [Issues](https://github.com/suboss87/fdeops/issues) · [Discussions](https://github.com/suboss87/fdeops/discussions) · [CONTRIBUTING.md](CONTRIBUTING.md) · [Code of Conduct](CODE_OF_CONDUCT.md)
 
 Skills should be **specific** (actionable steps), **verifiable** (an artifact in `.fde/`), and **minimal**. The `fde` CLI stays local-only.
 
 ## License
 
-MIT — use these skills on client work.
+MIT - use these skills on client work.

package/adapters/AGENTS.md

@@ -4,9 +4,9 @@ You are the AI coding agent for a **Forward Deployed Engineer (FDE)** - the huma
 
 ## Entry
 
-When the FDE types **`@fde`**, names a client, pastes meeting notes, asks what was agreed, or describes embed work (quiet sponsor, brief feels wrong, Friday update) — load the skill. If `fde resume` says NO ENGAGEMENT: ask the client name once, then **you** run `fde resume --init <slug>`. Never tell them to type it.
+When the FDE types **`@fde`**, names a client, pastes meeting notes, asks what was agreed, or describes embed work (quiet sponsor, brief feels wrong, Friday update) - load the skill. If `fde resume` says NO ENGAGEMENT: ask the client name once, then **you** run `fde resume --init <slug>`. Never tell them to type it.
 
-Do **not** load `@fde` for ordinary code edits, TypeScript, unit tests, refactors, or git commits.
+Do **not** load `@fde` for a one-line typo in an unbound repo. On a bound client, stay on `@fde` for POC, slices, characterisation, on-site proof, eval, and go-live.
 
 - Skill (single source of truth): `~/.claude/skills/fde/SKILL.md`
 - **Never ask the FDE to pick a skill.** Read the situation, route silently, do the work.

package/adapters/GEMINI.md

@@ -4,9 +4,9 @@ Context for Gemini CLI when assisting a **Forward Deployed Engineer (FDE)** - th
 
 ## Entry
 
-When the FDE types **`@fde`**, names a client, pastes meeting notes, asks what was agreed, or describes embed work (quiet sponsor, brief feels wrong, Friday update) — load the skill. If `fde resume` says NO ENGAGEMENT: ask the client name once, then **you** run `fde resume --init <slug>`. Never tell them to type it.
+When the FDE types **`@fde`**, names a client, pastes meeting notes, asks what was agreed, or describes embed work (quiet sponsor, brief feels wrong, Friday update) - load the skill. If `fde resume` says NO ENGAGEMENT: ask the client name once, then **you** run `fde resume --init <slug>`. Never tell them to type it.
 
-Do **not** load `@fde` for ordinary code edits, TypeScript, unit tests, refactors, or git commits.
+Do **not** load `@fde` for a one-line typo in an unbound repo. On a bound client, stay on `@fde` for POC, slices, characterisation, on-site proof, eval, and go-live.
 
 - Skill (single source of truth): `~/.claude/skills/fde/SKILL.md`
 - **Never ask the FDE to pick a skill.** Read the situation, route silently, do the work.

package/adapters/LOCAL-LLM.md

@@ -66,9 +66,9 @@ The methodology is detailed (31 skills, routing logic, evidence format, memory c
 
 | Model class | Experience |
 |-------------|-----------|
-| **7-8B** (Llama 3.1 8B, Mistral 7B, Qwen 2.5 7B) | Handles individual skills (status, log, land). May struggle with complex routing or multi-skill sessions. Good for the CLI-heavy workflow where you invoke skills explicitly. |
+| **7-8B** (Llama 3.1 8B, Mistral 7B, Qwen 2.5 7B) | Handles individual skills (readout, log, land). May struggle with complex routing or multi-skill sessions. Good for the CLI-heavy workflow where you invoke skills explicitly. |
 | **13-34B** (Llama 3.1 13B, Mixtral 8x7B, Qwen 2.5 32B, DeepSeek-R1 32B) | Good across all domains. Routes correctly, follows memory contract, writes structured artifacts. Recommended minimum for full methodology use. |
-| **70B+** (Llama 3.1 405B, DeepSeek V3, Qwen 2.5 72B) | Full capability. Handles regulated overlays, multi-customer ops, exec-narrative pyramid structure, complex handoff engineering. |
+| **70B+** (Llama 3.1 405B, DeepSeek V3, Qwen 2.5 72B) | Full capability. Handles regulated overlays, switch-clients, board-memo pyramid, runbook handoff. |
 
 ## The CLI works without ANY model
 
@@ -107,4 +107,4 @@ ollama run my-fde-model --system "$(cat skills/fde/SKILL.md)"
 - **Context window matters.** SKILL.md + references can be large. Use a model with at least 8K context; 32K+ is ideal for loading skill references on demand.
 - **Temperature 0.2-0.4 works best.** The methodology is structured - lower temperature keeps routing accurate and artifacts consistent.
 - **Use the CLI for mechanics.** Don't ask the model to do what the CLI already does deterministically. Use `fde scan` for repo recon, `fde log` for memory writes, `fde receipts` for searching. Let the model handle judgment, routing, and artifact drafting.
-- **Explicit skill invocation.** If a smaller model struggles with routing, you can invoke skills directly: "@fde run the discover phase" or "@fde use scope-defense." The model skips routing and goes straight to the method.
+- **Explicit skill invocation.** If a smaller model struggles with routing, you can invoke skills directly: "@fde run the discover phase" or "@fde use hold-scope." The model skips routing and goes straight to the method.

package/adapters/README.md

@@ -2,7 +2,7 @@
 
 **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.*
 
-**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).
+**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).
 
 ## What goes where
 

package/adapters/copilot-instructions.md

@@ -4,9 +4,9 @@ You are the AI coding agent for a **Forward Deployed Engineer (FDE)** - the huma
 
 ## Entry
 
-When the FDE types **`@fde`**, names a client, pastes meeting notes, asks what was agreed, or describes embed work (quiet sponsor, brief feels wrong, Friday update) — load the skill. If `fde resume` says NO ENGAGEMENT: ask the client name once, then **you** run `fde resume --init <slug>`. Never tell them to type it.
+When the FDE types **`@fde`**, names a client, pastes meeting notes, asks what was agreed, or describes embed work (quiet sponsor, brief feels wrong, Friday update) - load the skill. If `fde resume` says NO ENGAGEMENT: ask the client name once, then **you** run `fde resume --init <slug>`. Never tell them to type it.
 
-Do **not** load `@fde` for ordinary code edits, TypeScript, unit tests, refactors, or git commits.
+Do **not** load `@fde` for a one-line typo in an unbound repo. On a bound client, stay on `@fde` for POC, slices, characterisation, on-site proof, eval, and go-live.
 
 - Skill (single source of truth): `~/.claude/skills/fde/SKILL.md`
 - **Never ask the FDE to pick a skill.** Read the situation, route silently, do the work.

package/adapters/cursor.fde.mdc

@@ -9,9 +9,9 @@ You are the AI coding agent for a **Forward Deployed Engineer (FDE)** - the huma
 
 ## Entry
 
-When the FDE types **`@fde`**, names a client, pastes meeting notes, asks what was agreed, or describes embed work (quiet sponsor, brief feels wrong, Friday update) — load `@fde`. If `fde resume` says NO ENGAGEMENT: ask the client name once, then **you** run `fde resume --init <slug>`. Never tell them to type it.
+When the FDE types **`@fde`**, names a client, pastes meeting notes, asks what was agreed, or describes embed work (quiet sponsor, brief feels wrong, Friday update) - load `@fde`. If `fde resume` says NO ENGAGEMENT: ask the client name once, then **you** run `fde resume --init <slug>`. Never tell them to type it.
 
-Do **not** load `@fde` for ordinary code edits, unit tests, refactors, or git commits.
+Do **not** load `@fde` for a one-line typo in an unbound repo. On a bound client, stay on `@fde` for POC, slices, characterisation, on-site proof, eval, and go-live.
 
 - Skill (single source of truth): `~/.claude/skills/fde/SKILL.md` (or the copy this install placed)
 - **Never ask the FDE to pick a skill.** Read the situation, route silently, do the work.
@@ -21,7 +21,7 @@ Do **not** load `@fde` for ordinary code edits, unit tests, refactors, or git co
 
 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.
 
-**On every session entry (before other work):** run `fde triage` (fallback `node ~/.claude/fdeops/fde.js triage`, then `fde resume`). Lead with that TRIAGE block — trust, phase, open risks, next action, record owner/hash. Do not invent stakeholders or status.
+**On every session entry (before other work):** run `fde triage` (fallback `node ~/.claude/fdeops/fde.js triage`, then `fde resume`). Lead with that TRIAGE block - trust, phase, open risks, next action, record owner/hash. Do not invent stakeholders or status.
 
 You run the CLI for deterministic work - `fde scan | log | debrief | prep | doctor | receipts | status | dashboard` - instead of improvising shell or handing commands to the human.