feat: add steno-mode skill for shorthand response compression and token saving

[AkashAi7]

What

Adds the steno-mode skill — a shorthand-first response compression mode that cuts ~40% of response tokens while keeping every code literal, command, path, and error message exactly intact.

Why

Long agent sessions burn output tokens on prose filler. Steno Mode compresses responses through consistent, readable shorthand rules (stable abbreviations, symbolic chains like \X -> Y -> Z, filler removal) rather than random truncation. Priority order is exactness > readability > compression, so technical precision is never sacrificed.

Details

• 4 compression levels: \lite, \brief\ (default), \court, \machine\
• Explicit protect-list: code blocks, commands, paths, identifiers, env vars, error text, versions stay verbatim
• Honest scope section: works well for code review / debugging / architecture summaries; explicitly defers to prose for tutorials, stakeholder comms, and teaching
• Benchmarked on 50+ samples across 7 categories with exact token counts (gpt-tokenizer): ~40% avg reduction, 100% literal accuracy — interactive benchmark at https://akashai7.github.io/stenographer-mode/demo/

Checklist

• 
  pm run skill:validate\ passes (all 371 skills valid)
• 
  pm start\ run — docs/README.skills.md updated
• Branch created from \main\
• No duplicate of existing skills (searched for steno/token/compress/shorthand/concise)

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[Copilot]

Pull request overview

Adds a new Agent Skill (steno-mode) to the skills/ catalog, plus the generated docs entry, enabling a shorthand-first response compression mode intended to reduce output tokens while preserving exact technical literals.

Changes:

• Added skills/steno-mode/SKILL.md defining Steno Mode rules, levels, examples, scope, and safety constraints.
• Updated docs/README.skills.md to include the new skill in the published skills index.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
skills/steno-mode/SKILL.md	New skill definition with activation/persistence contract, compression rules, level behaviors, examples, and safety/scope guidance.
docs/README.skills.md	Adds the new steno-mode entry to the generated skills README table.

[github-actions]

🔍 Vally Lint Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	npm warn EBADENGINE Unsupported engine {
ℹ️	npm warn EBADENGINE package: 'commander@15.0.0',
ℹ️	npm warn EBADENGINE required: { node: '>=22.12.0' },
ℹ️	npm warn EBADENGINE current: { node: 'v20.20.2', npm: '10.8.2' }
ℹ️	npm warn EBADENGINE }
ℹ️	npm warn deprecated prebuild-install@7.1.3: No longer maintained. Please contact the author of the relevant native addon; alternatives are available.
ℹ️	✅ steno-mode (2/2 checks passed)
ℹ️	✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️	✓ spec-compliance: All spec checks passed.
ℹ️	✓ [valid-refs] All file references across 1 skill(s) are valid.

Full linter output

### Linting skills/steno-mode
npm warn EBADENGINE Unsupported engine {
npm warn EBADENGINE   package: 'commander@15.0.0',
npm warn EBADENGINE   required: { node: '>=22.12.0' },
npm warn EBADENGINE   current: { node: 'v20.20.2', npm: '10.8.2' }
npm warn EBADENGINE }
npm warn deprecated prebuild-install@7.1.3: No longer maintained. Please contact the author of the relevant native addon; alternatives are available.
✅ steno-mode (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed

[github-actions]

🔒 PR Risk Scan Results

Scanned 2 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	1
ℹ️ Info	0

Severity	Rule	File	Line	Match
🟠	package-exec-command	docs/README.skills.md	31	| [acreadiness-assess](../skills/acreadiness-assess/SKILL.md)<br />`gh skills install github/awesome-copilot acreadiness-assess` | Run the AgentRC readiness assessment on the curre

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[Copilot]

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.