golem15/msd-core
4
0
Fork 0
Code Issues 1 Pull Requests Actions 3 Packages Projects Releases Wiki Activity

feat(#769): adopt context:fork + effort on heavy workflow skills (#820)

Browse Source 
* feat(#769): emit context:fork + effort: frontmatter on heavy workflow skills

Add `context: fork` and `effort: xhigh` to the three heaviest workflow
commands (plan-phase, execute-phase, autonomous) and `effort: low` to the
two quick-status commands (progress, stats).

On Claude Code, `context: fork` runs the skill in an isolated subagent
context window so the main session's context budget is protected.
`effort: xhigh` / `effort: low` signal the appropriate token-budget tier to
the runtime. Both fields are silently ignored by runtimes that do not
recognise them (Gemini, Codex, Cursor, etc.) — no behaviour change outside
Claude Code.

Update convertClaudeCommandToClaudeSkill in bin/install.js to preserve
`context:` and `effort:` when rewriting source command files to SKILL.md for
a Claude global install. Add install-suite tests to assert the fields are
present in both source commands and the installed SKILL.md output.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* test(#769): tighten regex assertions + add execute/plan-phase effort coverage

Fix low-severity adversarial finding: tighten test regex patterns from
`\s*` to `[ \t]*` so they cannot match across newlines (CRLF parity).
Add missing effort: xhigh assertions for gsd-execute-phase and gsd-plan-phase
SKILL.md install output to complete the black-box coverage gap.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
2026-06-07 18:56:30 -04:00
committed by GitHub
parent 19280510fe
commit 41f91b2e88
9 changed files with 348 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
bin/install.js
View File

@@ -1988,6 +1988,10 @@ function convertClaudeCommandToClaudeSkill(content, skillName, runtime = null, c
const description = extractFrontmatterField(frontmatter, 'description') || '';
const argumentHint = extractFrontmatterField(frontmatter, 'argument-hint');
const agent = extractFrontmatterField(frontmatter, 'agent');
// #769: preserve context: and effort: from source command files so they
// are emitted into the installed SKILL.md frontmatter unchanged.
const context = extractFrontmatterField(frontmatter, 'context');
const effort = extractFrontmatterField(frontmatter, 'effort');
// Preserve allowed-tools as YAML multiline list (Claude native format)
const toolsMatch = frontmatter.match(/^allowed-tools:\s*\n((?:\s+-\s+.+\n?)*)/m);
@@ -2007,6 +2011,12 @@ function convertClaudeCommandToClaudeSkill(content, skillName, runtime = null, c
if (runtime === 'hermes') fm += `version: ${yamlQuote(pkg.version)}\n`;
if (argumentHint) fm += `argument-hint: ${yamlQuote(argumentHint)}\n`;
if (agent) fm += `agent: ${agent}\n`;
// #769: emit context: and effort: when present so the runtime can honour
// them natively (context: fork = isolated subagent window; effort: =
// token-budget tier). Fields are Claude-specific; unknown frontmatter
// fields are silently ignored by other runtimes (backward-compatible).
if (context) fm += `context: ${context}\n`;
if (effort) fm += `effort: ${effort}\n`;
if (toolsBlock) fm += toolsBlock;
fm += '---';