instruction-budget-audit
Use when creating, reviewing, splitting, or optimising Copilot instructions, agents, prompts, or skills for context cost.
Skill by hmlendea
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hmlendea-instruction-budget-audit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, finance
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/instruction-budget-audit
What's inside
- Skill name
instruction-budget-audit- Description
- Use when creating, reviewing, splitting, or optimising Copilot instructions, agents, prompts, or skills for context cost.
- License
- GPL-3.0
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Optimise context without changing policy outcomes. - Inventory words/bytes and activation: always-on, `applyTo`, semantic on-demand, or manual. - Measure automatic payload for representative paths; file size alone is not context cost. - Prioritise verbose output, large always-on sources, injected tool schemas, repeated reads, then minor prompt wording. - Always-on: universal invariants only. Move domain/workflow rules to narrow `applyTo` or semantic discovery. - Keep one concern per file; remove only rules guaranteed by a co-activated source. - Preserve protected mappings, templates, examples, thresholds, exceptions, and public contracts; hash or count them before/after mechanical edits. - Prefer compact declarative invariants over procedural repetition. - Keep model, reasoning effort, agent, skill, and tool configuration stable during a session; use `session-handoff` when changing them. - Validate frontmatter, activation, required rules, whitespace, and focused representative tasks after each slice. - Report baseline, changed surfaces, measured payload reduction, and residual risk; never infer billing savings from file size or request count.
From hmlendea/github-copilot-memories, GPL-3.0.
More from hmlendea/github-copilot-memories
- 0.559score
ai-credit-routing
hmlendea
Use when minimising GitHub Copilot AI credits, selecting a mode or model, reducing tool overhead, or deciding whether to start a fresh session.
SkillAFreshness: AClaude Code +9 - 0.559score
structured-data-query
hmlendea
Use when only specific fields or records are required from JSON, YAML, XML, CSV, API responses, manifests, lock files, or other structured data.
SkillAFreshness: AClaude Code +9 - 0.559score
repository-orientation
hmlendea
Use when repository structure, architecture, documentation, conventions, or project context must be discovered before a change.
SkillAFreshness: AClaude Code +9 - 0.559score
session-handoff
hmlendea
Use when changing task, topic, model, reasoning effort, agent, or tool set, or when accumulated conversation context is no longer relevant.
SkillAFreshness: AClaude Code +9 - 0.559score
symbol-navigation
hmlendea
Use when locating symbol definitions, references, implementations, call sites, or structurally similar code without reading broad file sets.
SkillAFreshness: AClaude Code +9 - 0.558score
signal-preserving-output
hmlendea
Use when builds, tests, linters, logs, Git commands, or other terminal operations may return verbose output.
SkillAFreshness: AClaude Code +9 - 0.558score
diff-first-review
hmlendea
Use when reviewing a change, pull request, patch, or diff for defects, regressions, risks, or missing tests.
SkillAFreshness: AClaude Code +9 - 0.558score
failure-triage
hmlendea
Use when a focused test, build, lint, type-check, or tool command fails during a task and the next repair is unclear.
SkillAFreshness: AClaude Code +9 - 0.558score
repository-defaults
hmlendea
Use when creating a project/repository, selecting its licence or default branch, merging branches, or pulling changes.
SkillAFreshness: AClaude Code +9 - 0.558score
scoped-context
hmlendea
Use when the relevant files are known.
SkillAFreshness: AClaude Code +9 - 0.557score
github-md-template-fidelity
hmlendea
Enforces 100% template fidelity for GitHub markdown files (README.md, ARCHITECTURE.md, CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md, PRIVACY.md…
SkillAFreshness: AClaude Code +9 - 0.556score
baseline-health
hmlendea
Use before changing code when test, build, lint, or type-check baseline status is unknown and pre-existing failures could cause rework.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 2, 2026 (27 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-3.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hmlendea
- 0.559score
session-handoff
hmlendea
Use when changing task, topic, model, reasoning effort, agent, or tool set, or when accumulated conversation context is no longer relevant.
SkillAFreshness: AClaude Code +9 - 0.559score
structured-data-query
hmlendea
Use when only specific fields or records are required from JSON, YAML, XML, CSV, API responses, manifests, lock files, or other structured data.
SkillAFreshness: AClaude Code +9 - 0.559score
symbol-navigation
hmlendea
Use when locating symbol definitions, references, implementations, call sites, or structurally similar code without reading broad file sets.
SkillAFreshness: AClaude Code +9 - 0.559score
repository-orientation
hmlendea
Use when repository structure, architecture, documentation, conventions, or project context must be discovered before a change.
SkillAFreshness: AClaude Code +9 - 0.559score
ai-credit-routing
hmlendea
Use when minimising GitHub Copilot AI credits, selecting a mode or model, reducing tool overhead, or deciding whether to start a fresh session.
SkillAFreshness: AClaude Code +9 - 0.558score
failure-triage
hmlendea
Use when a focused test, build, lint, type-check, or tool command fails during a task and the next repair is unclear.
SkillAFreshness: AClaude Code +9
Cite this page
instruction-budget-audit skill. Agent Mart. https://agentmart.dev/skills/hmlendea-instruction-budget-audit (last updated 2026-10-24)