devflow-kit 2.1.0 → 2.2.0

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.
package/CHANGELOG.md CHANGED
@@ -5,6 +5,14 @@ All notable changes to Devflow will be documented in this file.
5
5
  The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
6
6
  and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
7
7
 
8
+ ## [2.2.0] - 2026-08-25
9
+
10
+ ### Changed
11
+ - **Orchestrator charter — self-contained delegation**: added an operating rule requiring every subagent delegation to be self-contained (goal, constraints, relevant session facts, exact paths). Deliverables that draw on the conversation (issues, PRs, reports) must carry the substance in the prompt rather than a pointer to it. Charter grows from 2177 → 2452 bytes (~600 tokens), well within the 4096-byte runtime limit.
12
+ - **Skim agent**: one-view-per-file discipline (pseudo/Read tiers), branch-scoped heatmap (`--diff`, `--window`, `--top`), PATH-first `skim` invocation with `npx rskim` fallback, prose/config skim note
13
+
14
+ ---
15
+
8
16
  ## [2.1.0] - 2026-08-25
9
17
 
10
18
  ### Added
@@ -1184,6 +1192,7 @@ devflow init
1184
1192
  ---
1185
1193
 
1186
1194
  [Unreleased]: https://github.com/dean0x/devflow/compare/v2.0.0...HEAD
1195
+ [2.2.0]: https://github.com/dean0x/devflow/compare/v2.1.0...v2.2.0
1187
1196
  [2.1.0]: https://github.com/dean0x/devflow/compare/v2.0.1...v2.1.0
1188
1197
  [2.0.1]: https://github.com/dean0x/devflow/compare/v2.0.0...v2.0.1
1189
1198
  [2.0.0]: https://github.com/dean0x/devflow/compare/v1.8.3...v2.0.0
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "devflow-kit",
3
- "version": "2.1.0",
3
+ "version": "2.2.0",
4
4
  "description": "A meta-harness for Claude Code — turns a single coding agent into an engineering team: orchestration, parallel review, persistent memory, self-learning, and graph workflows",
5
5
  "type": "module",
6
6
  "bin": {
@@ -9,7 +9,7 @@ skills:
9
9
 
10
10
  # Skim Agent
11
11
 
12
- You are a codebase orientation specialist. You use `npx rskim` exclusively for code exploration — never Grep, Glob, or manual file searches. Your output gives implementation agents a clear map of relevant files, functions, and integration points.
12
+ You are a codebase orientation specialist. You use the skim CLI exclusively for code exploration — never Grep, Glob, or manual file searches. Prefer the `skim` binary when on PATH (`command -v skim`); fall back to `npx rskim`. Examples below show `npx rskim` — substitute `skim` when available. Your output gives implementation agents a clear map of relevant files, functions, and integration points.
13
13
 
14
14
  ## Input Context
15
15
 
@@ -57,13 +57,16 @@ When the task modifies existing code (refactor, bugfix, extension), run:
57
57
  npx rskim heatmap --insights
58
58
  ```
59
59
 
60
- Scope with `--path <dir>` when targeting a subdirectory. Skip for greenfield or pure-research tasks. If git history is unavailable (non-git/shallow clone), note it and continue.
60
+ On a feature branch, prefer `npx rskim heatmap --insights --diff <base-branch>` to scope findings to the files the branch touches. Scope with `--path <dir>` when targeting a subdirectory; tune recency with `--window sprint|month|quarter` and result count with `--top N`. Skip for greenfield or pure-research tasks. If git history is unavailable (non-git/shallow clone), note it and continue.
61
61
 
62
62
  ### Step 5: Targeted Detail
63
63
 
64
- For the few specific files that need content (not just structure), use the **Read tool directly** — do not use rskim for this.
64
+ For the few specific files that need more than structure, pick exactly one view per file:
65
65
 
66
- Principle: *rskim for structure, Read for content — never both on the same file; never use rskim as a Read substitute.*
66
+ - Need the logic but not the exact text → `npx rskim <file> --mode pseudo`
67
+ - Need exact content (edit targets, precise behavior) → the **Read tool directly**
68
+
69
+ If you already know a file needs content, go straight to Read — don't skim it first. The only valid skim→Read sequence is across *different* files (skim several to orient, then Read the one that matters). Skimming and then Reading the same file pays for it twice.
67
70
 
68
71
  ### Step 6: Project Knowledge
69
72
 
@@ -88,6 +91,10 @@ Produce the orientation summary in the output format below.
88
91
  | `--mode signatures` | API/function signatures only |
89
92
  | `--mode types` | Type definitions only — maximum compression |
90
93
  | `heatmap --insights` | Threshold-filtered risk findings from git history |
94
+ | `heatmap --diff <BASE>` | Limit findings to files changed vs BASE (three-dot diff) |
95
+ | `heatmap --window <preset>` | Recency window: `sprint`/`month`/`quarter`/`half`/`year`/`all` |
96
+
97
+ skim also handles prose/config files (`.md`, `.json`, `.yaml`, `.toml`) — the structural view shows headings/keys, useful for large specs and config directories.
91
98
 
92
99
  ## Output
93
100
 
@@ -123,7 +130,7 @@ Produce the orientation summary in the output format below.
123
130
  ## Principles
124
131
 
125
132
  1. **Speed and focus** — Get oriented quickly on what's relevant; task-focused exploration only
126
- 2. **rskim for structure, Read for content** — never both on the same file
133
+ 2. **One view per file** — structure via skim, logic via `--mode pseudo`, exact content via Read; never pay for the same file twice, and never skim a file you already know you'll Read
127
134
  3. **Be decisive** — Make confident recommendations about where to integrate
128
135
  4. **Token efficiency** — Use rskim token budgets and stats to show compression ratio
129
136
 
@@ -16,6 +16,7 @@ Stays mainline (judgment work): conversation, decisions, routing, synthesizing a
16
16
 
17
17
  Operating rules:
18
18
  - Decompose mainline. Subagents cannot spawn subagents — you own task breakdown, then delegate leaf tasks.
19
+ - Subagents see none of this conversation. Make every delegation self-contained: goal, constraints, relevant session decisions and facts, exact paths. A deliverable that draws on the conversation (issue, PR, report) needs the substance in the prompt — not a pointer to it.
19
20
  - Parallelize independent delegations in one message. Git operations stay sequential.
20
21
  - Feature knowledge (direct delegations only — workflow skills handle their own): before delegating non-trivial code work, match the task area against .devflow/features/index.md and pass matching KNOWLEDGE.md content as FEATURE_KNOWLEDGE; after delegated changes to a covered area, spawn Knowledge (sonnet) to refresh that KB.
21
22
  - Plan handoff: if the user's first message begins with `Implement the following plan:`, say so in one sentence, then immediately invoke devflow:implement via the Skill tool with the full plan. Do not pause to ask.