fdeops 3.5.2 → 3.5.3

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 (2) hide show
  1. package/README.md +52 -38
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -20,7 +20,7 @@ flowchart LR
20
20
  B --> F["Build & Guard"]
21
21
  B --> G["Ship & Verify"]
22
22
  B --> H["Operate & Close"]
23
- C --> I[".fde/ memory\n(auto-written)"]
23
+ C --> I[".fde/ memory\n(written as you work)"]
24
24
  D --> I
25
25
  E --> I
26
26
  F --> I
@@ -48,7 +48,7 @@ Works with **Claude Code** · **Cursor** · **Copilot** · **Devin** · **Gemini
48
48
  | **Agency engineer running 3-5 clients** | Client details blur together. One `.fde/` per customer, never cross-contaminated. |
49
49
  | **Forward Deployed Engineer** | The role this was built for. 34 skills across the full engagement lifecycle. |
50
50
  | **Technical founder doing client work solo** | You ARE the team. The agent becomes your second brain. |
51
- | **Enterprise programme lead** | Running AI transformations? Built-in methods for model selection, agent safety, governance, and cost management. |
51
+ | **Enterprise programme lead** | Leading AI transformations? Built-in methods for model selection, agent safety, governance, and cost management. |
52
52
 
53
53
  ---
54
54
 
@@ -56,10 +56,10 @@ Works with **Claude Code** · **Cursor** · **Copilot** · **Devin** · **Gemini
56
56
 
57
57
  | | **Without fdeops** | **With fdeops** |
58
58
  |---|-------------------|----------------|
59
- | **Memory** | Re-paste context every session | `.fde/` writes itself - next session starts where today ended |
60
- | **Discovery** | Agent treats the brief as the task | Agent scans churn, test gaps, "temporary" code; hands you the real problem with evidence |
61
- | **Multiple customers** | Details blur between clients | One folder per customer, auto-loaded, never merged |
62
- | **The output** | Advice you already knew | An artifact you carry into the sponsor meeting |
59
+ | **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" |
60
+ | **Scope creep** | Five "small" additions absorbed silently, timeline slips | Receipts timestamped you walk into the sponsor meeting with evidence |
61
+ | **Multiple customers** | Wrong client name in a status update, details blur | One folder per customer, context-switch protocol, cross-contamination checklist |
62
+ | **The sponsor meeting** | "We completed the API endpoint" | "Manual reconciliation dropped from 3 FTEs to 0.5 — here's the rollback if it turns" |
63
63
 
64
64
  ---
65
65
 
@@ -67,60 +67,74 @@ Works with **Claude Code** · **Cursor** · **Copilot** · **Devin** · **Gemini
67
67
 
68
68
  **Requires:** [Node.js](https://nodejs.org) >= 18
69
69
 
70
- ```bash
71
- # Option A: Skills CLI (any agent)
72
- npx skills add suboss87/fdeops
73
-
74
- # Option B: Clone + install
75
- git clone https://github.com/suboss87/fdeops.git
76
- cd fdeops && node bin/install.js
77
- ```
70
+ ### 1. Install and create your first engagement
78
71
 
79
- Start your first engagement:
80
72
  ```bash
81
- node bin/install.js init my-client
82
- # or: npx fdeops init my-client (engagement memory at ~/fde-engagements/my-client/.fde/)
73
+ npx fdeops init my-client # creates engagement memory at ~/fde-engagements/my-client/.fde/
83
74
  ```
84
75
 
85
- Point the AI coding agent at it:
76
+ ### 2. Point your AI agent at it
77
+
86
78
  ```bash
87
79
  export FDEOPS_ENGAGEMENT=~/fde-engagements/my-client/.fde
88
80
  ```
89
81
 
90
- Then talk to your agent:
82
+ ### 3. Start working
83
+
91
84
  ```
92
85
  @fde I'm on site. First stakeholder meeting tomorrow. Brief says fix the payments API.
93
86
  ```
94
87
 
95
- The system routes to `land` and starts working:
88
+ The agent routes to `land` and starts thinking with you:
89
+
96
90
  ```
97
- Routing to: land (first engagement, day 1)
91
+ Brief says payments API but nobody named who owns the budget for this
92
+ work. That's your first question tomorrow. And the brief has no
93
+ out-of-scope section, which means scope creep is pre-authorised.
94
+
95
+ Watch for the internal dev who got passed over for this contract — if
96
+ there is one, you want them on your side before the first standup.
97
+ Also: what does failure look like to the sponsor personally, not the
98
+ project charter? That answer shapes everything.
98
99
 
99
- Before tomorrow's meeting, I need to understand a few things:
100
+ I'll draft brief.md, success.md, stakeholders.md, trust-profile.md
101
+ after you come back with notes.
102
+ ```
100
103
 
101
- 1. Who owns the budget for this work? (the brief doesn't say)
102
- 2. What's NOT in scope? (undefined scope = unlimited scope)
103
- 3. Is there an internal dev who was passed over for this work?
104
- 4. What's their AI policy? (do they know I'm an AI agent?)
104
+ Day 15, the memory has compounded:
105
105
 
106
- Writing: brief.md, success.md, stakeholders.md, trust-profile.md
107
- Next: bring answers from the meeting, then we discover the real problem.
106
+ ```
107
+ @fde What's the priority today?
108
108
  ```
109
109
 
110
- That's it. The system takes over from there.
110
+ ```
111
+ Last session you were finishing the ingest retry on staging. CTO demo
112
+ is Friday and status hasn't gone out since Tuesday. The finance
113
+ controller still hasn't seen a working demo — that's a risk.
114
+
115
+ Globex has been quiet for 3 days — trust signal amber.
116
+
117
+ I'd send the CTO status first, then finish the retry, then check in
118
+ on Globex before end of day. What do you want to tackle?
119
+ ```
120
+
121
+ That's the difference. Day 1: it coaches your preparation. Day 15: it picks up where yesterday ended and triages across customers.
122
+
123
+ > **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).
124
+
125
+ ---
111
126
 
112
- ### Use it in any tool
127
+ ## Works with any AI coding tool
113
128
 
114
129
  One skill file powers every tool. Install adapters for your setup:
115
130
 
116
131
  ```bash
117
- node bin/install.js adapters ~/fde-engagements/my-client
118
- # or: npx fdeops@latest adapters ~/fde-engagements/my-client
132
+ npx fdeops adapters ~/fde-engagements/my-client
119
133
  ```
120
134
 
121
- | Tool | Pointer file it reads |
122
- |------|-----------------------|
123
- | Claude Code | plugin + `~/.claude/FDEOPS-CLAUDE.md` |
135
+ | Tool | What it reads |
136
+ |------|--------------|
137
+ | Claude Code | Plugin + `~/.claude/FDEOPS-CLAUDE.md` |
124
138
  | Codex / OpenAI / generic | `AGENTS.md` |
125
139
  | Gemini CLI | `GEMINI.md` |
126
140
  | Cursor | `.cursor/rules/fde.mdc` |
@@ -134,8 +148,8 @@ Each adapter points at the same `@fde` skill, so the methodology and memory stay
134
148
 
135
149
  ```text
136
150
  YOU (human) AI CODING AGENT (software)
137
- meetings, judgment @fde routes -> right skill -> does the work
138
- | -----> .fde/ memory (self-writing)
151
+ meetings, judgment @fde routes -> right skill -> drafts the artifact
152
+ | -----> .fde/ memory (written as you work)
139
153
  | |
140
154
  +---------------> client workspace (code, VPN, tickets)
141
155
  ```
@@ -153,7 +167,7 @@ Each adapter points at the same `@fde` skill, so the methodology and memory stay
153
167
  | **Embed & Trust** | land, audit, stakeholder-radar, trust-engineering, scope-defense | First days: access, credibility, scope |
154
168
  | **Discover & Diagnose** | discover, assumption-audit, use-case-scoring, sketch | Finding the real problem behind the brief |
155
169
  | **Plan & Align** | plan, business-case, options-analysis, initiative-triage | Sequencing work, getting sponsor alignment |
156
- | **Build & Guard** | build, incremental-build, test-on-legacy, blast-radius, debug, rescue, security-audit, observability | Safe implementation on their codebase |
170
+ | **Build & Guard** | build, incremental-build, test-on-legacy, blast-radius, debug, rescue, security-audit, observability | Helping you build safely on their codebase |
157
171
  | **Ship & Verify** | ship, review, rollback-drill, qa-live | Getting to production without surprises |
158
172
  | **Operate & Close** | status, demo-prep, debrief, exec-narrative, dashboard, multi-customer-ops, close, handoff-engineering, pattern-extract | Running and ending the engagement well |
159
173
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "fdeops",
3
- "version": "3.5.2",
3
+ "version": "3.5.3",
4
4
  "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.",
5
5
  "bin": {
6
6
  "fdeops": "bin/install.js",