converge

Name: converge
Author: Rune-kit

80stars21forks

How to install converge?

rune-kit/rune/converge

$npx -y skills add Rune-kit/rune --skill converge

Installs into the current project.

Summary

Spec↔code convergence scan. Use after implementation to verify the ACTUAL codebase matches the spec/plan — detects missing backends, dead buttons, partial wiring, scope creep. Classifies gaps (missing/partial/contradicts/unrequested), appends remediation tasks, loops until conver

Files · 1

View on GitHub

SKILL.md

1	# converge
2
3	## Purpose
4
5	Post-implementation gap detector. Re-reads the spec, plan, and tasks as the sole source of intent, inspects the ACTUAL codebase (present state, not the diff), and classifies every intent key as implemented or gapped. Where verification asks "does it build?", converge asks "is everything the spec promised actually in the code?"
6
7	This is the skill that catches the most expensive silent failure: a P1 story's UI exists, renders, passes lint/type/build — and its backend was never written.
8
9	<HARD-GATE>
10	Converge DETECTS — it never fixes. No Edit, no Write to source files.
11	Its ONLY write is APPENDING a `## Convergence` task section to the plan's task file.
12	Existing file content is never rewritten, reordered, or deleted. Zero gaps = zero writes.
13	</HARD-GATE>
14
15	## Called By (inbound)
16
17	- `cook` (L1): Phase 6.5 CONVERGE — after VERIFY, before COMMIT, for feature/greenfield chains with a requirements.md
18	- User: `/rune converge` — "did it fully implement the spec?", "check completeness", "does the code match the spec?"
19
20	## Calls (outbound)
21
22	None — pure L3 verification utility. Reports gaps; cook decides what to execute.
23
24	## Executable Steps
25
26	### Step 1 — Build the Intent Inventory
27
28	Load intent sources (all that exist; requirements.md is mandatory — without it, STOP and report `NO_SPEC`):
29
30	1. `.rune/features/<name>/requirements.md` — extract keys: every `FR-n`, every `US-n` with priority + Independent Test, every `AC-n.m` (as `US-n/AC-n.m`), every Key Entity
31	2. `.rune/plan-<feature>.md` + phase files — Key Decisions, Coverage Summary, task list with `P<phase>-T<seq>` IDs
32	3. `.rune/features/<name>/contracts/*.md` — each contract: its endpoint, its `Serves:` story, its `Consumers:` list
33	4. `.rune/features/<name>/data-model.md` — entities, state transitions
34	5. `.rune/features/<name>/quickstart.md` — per-story validation steps
35	6. `.rune/ui-spec.md` `## Unwired Elements` (if present) — designed placeholders that MUST NOT count as implemented
36
37	The inventory is a flat list of keys: `FR-3`, `US-1/AC-1.2`, `contract:create-order`, `entity:Order`, `decision:<slug>`.
38
39	Rules:
40	- Task IDs (`P<phase>-T<seq>`) and quickstart.md are EVIDENCE, not verdict keys — tasks feed the code-scope map (Step 2), quickstart steps feed pass/fail evidence for story rows. Neither gets its own verdict row
41	- US-n verdict is DERIVED: worst verdict among its `AC-n.m` rows (all ACs implemented → story implemented; any partial/missing → story inherits it). Don't independently re-assess the story
42	- Plan Claims vs Reality: while reading tasks, note every task marked `[x]` whose artifact is missing/partial in code — these go in a dedicated report section (informational; `completion-gate` owns claim enforcement, converge just surfaces the lie)
43
44	### Step 2 — Build the Code-Scope Map
45
46	Map intent → code locations. NO full-repo read — targeted lookups only:
47
48	1. `Glob` every file path named in plan tasks — does it exist?
49	2. `Grep` entity names (from data-model.md) across schema/model directories
50	3. `Grep` each contract's endpoint path/route across the codebase — implementation AND callers
51	4. `Grep` component names from UI tasks — definition AND the handler symbols they bind
52
53	### Step 3 — Classify Gaps
54
55	For every intent key, assign exactly one verdict:
56
57	\| Verdict \| Meaning \| Example \|
58	\|---------\|---------\|---------\|
59	\| `implemented` \| Code fully realizes the key \| Endpoint exists, has logic, has a caller \|
60	\| `missing` \| Required work absent entirely \| Contract file exists, no route implements it \|
61	\| `partial` \| Started but a link in the chain is dead \| Button + handler exist; handler's fetch targets a route that doesn't exist \|
62	\| `contradicts` \| Code diverges from a locked decision or AC \| Spec says soft-delete; code hard-deletes \|
63	\| `unrequested` \| Code maps to NO intent key (scope creep — surfaced, not blocked) \| New admin page no story asked for \|
64
65	Dead-interaction trace (run for every UI element an AC references):
66
67	```
68	element → handler bound? → handler body non-trivial? → calls service/fetch?
69	→ target route/function EXISTS in codebase? → route touches the entity the AC names?
70	```
71
72	First broken link = `partial`, keyed to that element's `US-n/AC-n.m`. Heuristics: `onClick={() => {}}`, `href="#"` on action links, `console.log`-only handlers, `preventDefault()`-only submits, `fetch('/api/...')` where no route file matches — all break th

People who liked this also viewed

6 picks

Type

converge

80stars21forks

View on GitHub

How to install converge?

rune-kit/rune/converge

$npx -y skills add Rune-kit/rune --skill converge

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# converge
2
3	## Purpose
4
5	Post-implementation gap detector. Re-reads the spec, plan, and tasks as the sole source of intent, inspects the ACTUAL codebase (present state, not the diff), and classifies every intent key as implemented or gapped. Where verification asks "does it build?", converge asks "is everything the spec promised actually in the code?"
6
7	This is the skill that catches the most expensive silent failure: a P1 story's UI exists, renders, passes lint/type/build — and its backend was never written.
8
9	<HARD-GATE>
10	Converge DETECTS — it never fixes. No Edit, no Write to source files.
11	Its ONLY write is APPENDING a `## Convergence` task section to the plan's task file.
12	Existing file content is never rewritten, reordered, or deleted. Zero gaps = zero writes.
13	</HARD-GATE>
14
15	## Called By (inbound)
16
17	- `cook` (L1): Phase 6.5 CONVERGE — after VERIFY, before COMMIT, for feature/greenfield chains with a requirements.md
18	- User: `/rune converge` — "did it fully implement the spec?", "check completeness", "does the code match the spec?"
19
20	## Calls (outbound)
21
22	None — pure L3 verification utility. Reports gaps; cook decides what to execute.
23
24	## Executable Steps
25
26	### Step 1 — Build the Intent Inventory
27
28	Load intent sources (all that exist; requirements.md is mandatory — without it, STOP and report `NO_SPEC`):
29
30	1. `.rune/features/<name>/requirements.md` — extract keys: every `FR-n`, every `US-n` with priority + Independent Test, every `AC-n.m` (as `US-n/AC-n.m`), every Key Entity
31	2. `.rune/plan-<feature>.md` + phase files — Key Decisions, Coverage Summary, task list with `P<phase>-T<seq>` IDs
32	3. `.rune/features/<name>/contracts/*.md` — each contract: its endpoint, its `Serves:` story, its `Consumers:` list
33	4. `.rune/features/<name>/data-model.md` — entities, state transitions
34	5. `.rune/features/<name>/quickstart.md` — per-story validation steps
35	6. `.rune/ui-spec.md` `## Unwired Elements` (if present) — designed placeholders that MUST NOT count as implemented
36
37	The inventory is a flat list of keys: `FR-3`, `US-1/AC-1.2`, `contract:create-order`, `entity:Order`, `decision:<slug>`.
38
39	Rules:
40	- Task IDs (`P<phase>-T<seq>`) and quickstart.md are EVIDENCE, not verdict keys — tasks feed the code-scope map (Step 2), quickstart steps feed pass/fail evidence for story rows. Neither gets its own verdict row
41	- US-n verdict is DERIVED: worst verdict among its `AC-n.m` rows (all ACs implemented → story implemented; any partial/missing → story inherits it). Don't independently re-assess the story
42	- Plan Claims vs Reality: while reading tasks, note every task marked `[x]` whose artifact is missing/partial in code — these go in a dedicated report section (informational; `completion-gate` owns claim enforcement, converge just surfaces the lie)
43
44	### Step 2 — Build the Code-Scope Map
45
46	Map intent → code locations. NO full-repo read — targeted lookups only:
47
48	1. `Glob` every file path named in plan tasks — does it exist?
49	2. `Grep` entity names (from data-model.md) across schema/model directories
50	3. `Grep` each contract's endpoint path/route across the codebase — implementation AND callers
51	4. `Grep` component names from UI tasks — definition AND the handler symbols they bind
52
53	### Step 3 — Classify Gaps
54
55	For every intent key, assign exactly one verdict:
56
57	\| Verdict \| Meaning \| Example \|
58	\|---------\|---------\|---------\|
59	\| `implemented` \| Code fully realizes the key \| Endpoint exists, has logic, has a caller \|
60	\| `missing` \| Required work absent entirely \| Contract file exists, no route implements it \|
61	\| `partial` \| Started but a link in the chain is dead \| Button + handler exist; handler's fetch targets a route that doesn't exist \|
62	\| `contradicts` \| Code diverges from a locked decision or AC \| Spec says soft-delete; code hard-deletes \|
63	\| `unrequested` \| Code maps to NO intent key (scope creep — surfaced, not blocked) \| New admin page no story asked for \|
64
65	Dead-interaction trace (run for every UI element an AC references):
66
67	```
68	element → handler bound? → handler body non-trivial? → calls service/fetch?
69	→ target route/function EXISTS in codebase? → route touches the entity the AC names?
70	```
71
72	First broken link = `partial`, keyed to that element's `US-n/AC-n.m`. Heuristics: `onClick={() => {}}`, `href="#"` on action links, `console.log`-only handlers, `preventDefault()`-only submits, `fetch('/api/...')` where no route file matches — all break th

People who liked this also viewed

6 picks

Type