gm-qwen 2.0.782 → 2.0.783
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/gm.json +1 -1
- package/package.json +1 -1
- package/skills/gm/SKILL.md +10 -0
- package/skills/planning/SKILL.md +10 -0
package/gm.json
CHANGED
package/package.json
CHANGED
package/skills/gm/SKILL.md
CHANGED
|
@@ -85,6 +85,16 @@ Pure-prose edits to static documents with no JS/canvas/DOM behavior change are e
|
|
|
85
85
|
|
|
86
86
|
This rule fires in EXECUTE (witness on edit), EMIT (post-emit verify), and VERIFY (final gate). All three.
|
|
87
87
|
|
|
88
|
+
## NOTHING FAKE — HARD RULE
|
|
89
|
+
|
|
90
|
+
What ships runs against real services, real data, real binaries. Stubs, mocks, placeholder returns, fixture-only paths, "TODO: implement", `return null /* fake */`, hardcoded sample responses, and demo-mode fallbacks are forbidden in source the user will run. They produce green checks that survive into production and lie about what works.
|
|
91
|
+
|
|
92
|
+
Scaffolding and shims are permitted when they call through to real behavior — an empty file laid down before its body, a thin adapter wrapping an upstream API, a build target that compiles but is wired to nothing yet *and is the only callsite of itself*. The test is whether the artifact, executed, would do the thing it claims. If it would not, it is a stub.
|
|
93
|
+
|
|
94
|
+
Before writing a shim or adapter, the agent asks whether an existing library or tool already provides the same surface. Maintaining a local reimplementation of something an upstream package solves is its own failure mode — the shim drifts, ages, and accumulates the bugs the upstream already fixed. If a published package fits, the shim becomes one line of import.
|
|
95
|
+
|
|
96
|
+
Stub detection is by behavior, not by keyword: code paths that always succeed, always return the same value regardless of input, or short-circuit a real call to satisfy a type signature, are stubs. Comments asserting realness do not make code real. The witnessing rule that closes a mutable also closes this one — until real input has produced real output through the new code, it is provisional, and shipping provisional code as done is forced closure.
|
|
97
|
+
|
|
88
98
|
## EXECUTION ORDER
|
|
89
99
|
|
|
90
100
|
1. Recall — `plugkit recall` for any familiar-feeling unknown (cheapest, 200 tokens)
|
package/skills/planning/SKILL.md
CHANGED
|
@@ -75,6 +75,16 @@ The trigger is functional, not a path-list: any change whose effect is observabl
|
|
|
75
75
|
|
|
76
76
|
Propagation: EXECUTE witnesses on edit, EMIT re-witnesses post-write, VERIFY runs the final gate. The plan must encode the rule so all three layers fire.
|
|
77
77
|
|
|
78
|
+
## NOTHING FAKE — HARD RULE
|
|
79
|
+
|
|
80
|
+
Plan items resolve when real input flows through real code into real output. Stubs, mocks, placeholder returns, fixture-only branches, "TODO: implement", and demo-mode short-circuits do not count as resolution — they are mutables wearing closed-status disguise.
|
|
81
|
+
|
|
82
|
+
Acceptance criteria must witness behavior, not the existence of a function with the right name. "X is implemented" is not acceptance; "X called with real Y produces real Z" is. The agent that satisfies the criterion via a stub has built something that will lie when production calls it.
|
|
83
|
+
|
|
84
|
+
Scaffolding and shims are permitted only when the shim *delegates* to real behavior — wraps an upstream API, calls a real subprocess, hits a real disk. Before adding a shim, the plan asks whether a published library or tool already provides that surface; maintaining a local reimplementation of an upstream solution is its own failure mode and the shim line should usually become an import line.
|
|
85
|
+
|
|
86
|
+
The fake-detection test is behavioral: would the code, executed against the inputs it claims to accept, produce the outputs it claims to produce? If the answer requires "after we fill in the body" or "once X is wired up", the plan item is open, not done.
|
|
87
|
+
|
|
78
88
|
## ORIENT — HARD RULE
|
|
79
89
|
|
|
80
90
|
Open every plan with a parallel pack of `exec:recall` and `exec:codesearch` against the request's nouns. Hits land as `weak_prior`; misses confirm the unknown is fresh. The pack runs in one message — never serially. The agent that skips orient pays the same cost in fresh probes a turn later, plus the price of disagreeing with its own prior witness.
|