Context Engineering
abashev/vfs-s3
Optimizes agent context setup. An agent skill from abashev/vfs-s3.
Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list.
Install Context Audit
$ npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills context-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/context-audit .claude/skills/context-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "context-audit" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/context-audit into .claude/skills/context-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/context-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills context-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/context-audit .agents/skills/context-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "context-audit" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/context-audit into .agents/skills/context-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills context-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/context-audit .cursor/skills/context-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "context-audit" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/context-audit into .cursor/skills/context-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Neeeophytee/finding-unknowns-skills.git --path skills/context-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills context-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/context-audit .gemini/skills/context-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "context-audit" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/context-audit into .gemini/skills/context-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Neeeophytee/finding-unknowns-skills context-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/context-audit .github/skills/context-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "context-audit" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/context-audit into .github/skills/context-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills context-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/context-audit .opencode/skills/context-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "context-audit" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/context-audit into .opencode/skills/context-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
context-audit- GitHub stars
- 343
- Token cost
- ~779 tokens
- SKILL.md length
- 442 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list.
- Works in 5 steps: Inventory every layer that reaches the… → Read them together, the way the model… → Classify every instruction as one of… → …
- An agent ignores its own instructions
- SKILL.md covers Steps and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Context Audit is an agent skill from Neeeophytee/finding-unknowns-skills. Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list. Use when an agent ignores its own instructions, when a CLAUDE.md has grown bloated, or when the user asks to audit or rightsize their agent context.
Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Agent instruction files and Codebase knowledge for agents. The repository describes itself as: 14 installable skills for Claude Code, OpenAI Codex, and Hermes: find unknowns, clarify requirements, manage context, test assumptions, and verify bug fixes with regression… The licence is MIT.
When your agent uses it
- An agent ignores its own instructions
- A CLAUDE.md has grown bloated
- The user asks to audit
- Rightsize their agent context
Example prompts
- “/context-audit”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Inventory every layer that reaches the model: root and nested CLAUDE.md/AGENTS.md, each skill's description and body, hooks, tool and MCP…
- Read them together, the way the model receives them — not one file at a time. Contradictions only exist between layers.
- Classify every instruction as one of five things
- Propose the cut as a diff: conflicts resolved first, then duplicates, then the rest. For anything that is worth keeping but only sometimes…
- Close with before/after line counts and the single deletion you are least confident about, named explicitly so a human decides that one.
What it can do on your machine
Read from SKILL.md and the folder at commit ca5696a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Context Audit loads about 779 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 442 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Neeeophytee/finding-unknowns-skills at commit ca5696a, republished under its MIT licence (© Neeeophytee). 442 words, ~779 tokens.
Download SKILL.mdSave it as
.claude/skills/context-audit/SKILL.md (or your agent's skills folder).- name
- context-audit
- description
- Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list. Use when an agent ignores its own instructions, when a CLAUDE.md has grown bloated, or when the user asks to audit or rightsize their agent context.
Context audit
A prompt is written for one task; context is reused across every task, so it can never be as specific. That gap is where instructions rot: rules written for a worst case that no longer happens, guidance duplicated across three layers, two layers quietly telling the model opposite things. The model can resolve all of it — by spending thinking budget on it before it starts your actual work. This skill finds what to delete.
Steps
- Inventory every layer that reaches the model: root and nested
CLAUDE.md/AGENTS.md, each skill's description and body, hooks, tool and MCP server descriptions, and any harness prompt the user controls. Report each layer's size. The layer the user forgot they wrote is usually the loudest one. - Read them together, the way the model receives them — not one file at a time. Contradictions only exist between layers.
- Classify every instruction as one of five things:
- Conflict — two layers pulling opposite ways ("document as appropriate" against "never add comments"). Quote both sides verbatim. These are the most expensive finding and go first.
- Duplicate — the same instruction in two places. Keep the copy nearest the point of use; behavior of a tool belongs in that tool's description, not in the global preamble.
- Obvious — restates what the file tree, the language, or the surrounding code already shows.
- Judgement-now — a blanket rule written to prevent a worst case, wrong for some real subset of requests, and the kind of call a current model makes well on its own.
- Gotcha — non-obvious, specific to this repo, load-bearing. This is what should survive; most repos are mostly the other four.
- Propose the cut as a diff: conflicts resolved first, then duplicates, then the rest. For anything that is worth keeping but only sometimes needed, propose relocating it into a skill or a linked file loaded on demand rather than deleting it.
- Close with before/after line counts and the single deletion you are least confident about, named explicitly so a human decides that one.
Show full SKILL.md (106 more words)Show less
Guardrails
- Propose, don't apply. The user approves every deletion.
- A rule that reads as over-constraint is sometimes scar tissue from a real incident. Anything naming a specific failure gets asked about, not cut.
- Judge instructions by whether they change behavior, not by whether they sound wise. A line the model already follows by default costs tokens to say nothing.
- If the harness ships its own rightsizing command, this runs alongside it, not instead of it.
- An audit that deletes a real invariant costs far more than the tokens it saved. When a line's purpose is unclear, that ambiguity is the finding — report it rather than guessing.
© Neeeophytee, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/context-audit of Neeeophytee/finding-unknowns-skills.
Open the folder on GitHubat commit ca5696a
Compare with similar skills
Context Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Context Audit this skillNeeeophytee/finding-unknowns-skills | 343 | — | ~779 | Automated safety check: Pass | MIT | |
| Context Engineeringabashev/vfs-s3 | 106 | 9 repos | ~2.6k | Automated safety check: Notes | Apache-2.0 | |
| Dotagents Standardgetknit/knit | 132 | — | ~4.1k | Automated safety check: Pass | MIT | |
| Reconcile ContextApocrathia/home-assistant-config | 179 | — | ~931 | Automated safety check: Pass | None | |
| Verify Agent ContextLuligu/matterbridge | 985 | — | ~525 | Automated safety check: Pass | Apache-2.0 | |
| Setup Calibercaliber-ai-org/ai-setup | 1.3k | — | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
Dotagents Standard
getknit/knit
Set up, author, and navigate the dotagents standard — a slim AGENTS.md "router" at the repository root plus a hidden .agents/ directory (rules, context, memory, personas, skills, specs, logs, tasks)…
Reconcile Context
Apocrathia/home-assistant-config
Fix drift in Home Assistant Homelab agent context (AGENTS.md, CLAUDE.md, .agents/context/, rules, skills, agents) against the repo.
Verify Agent Context
Luligu/matterbridge
Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/.
Setup Caliber
caliber-ai-org/ai-setup
Sets up Caliber for automatic AI agent context sync. An agent skill from caliber-ai-org/ai-setup.
Agent Context Loader
jeremylongshore/tons-of-skills-marketplace
Execute proactive auto-loading: automatically detects and loads agents.md files.
More from Neeeophytee/finding-unknowns-skills
All 14 skills in this repoAgent Interface Design
Neeeophytee/finding-unknowns-skills
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.
Assumption Test
Neeeophytee/finding-unknowns-skills
Test a consequential technical assumption with a small, falsifiable experiment before committing to an approach.
Blindspot Pass
Neeeophytee/finding-unknowns-skills
Surface the user's unknown unknowns before work starts. An agent skill from Neeeophytee/finding-unknowns-skills.
Brainstorm Prototypes
Neeeophytee/finding-unknowns-skills
Generate several genuinely different throwaway variations (designs, approaches, drafts) for the user to react to.
Change Quiz
Neeeophytee/finding-unknowns-skills
After a working session, produce a report on what changed plus a quiz the user must pass before merging.
Implementation Notes
Neeeophytee/finding-unknowns-skills
Keep a running implementation-notes.md during a build, logging every deviation from the plan and every discovered edge case.
Related
Categories
Questions about Context Audit
What does Context Audit do?
Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list. Context Audit is an agent skill from Neeeophytee/finding-unknowns-skills.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list.
When should I use Context Audit?
Context Audit fits situations like: an agent ignores its own instructions; A CLAUDE.md has grown bloated; the user asks to audit; rightsize their agent context.
How do I install Context Audit in Claude Code?
Run `npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a claude-code`. Or copy the skill folder (skills/context-audit in Neeeophytee/finding-unknowns-skills) into .claude/skills/context-audit in your project. Claude Code loads it when a task matches its description.
How do I install Context Audit in Codex?
Run `npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a codex`. Or copy the skill folder (skills/context-audit in Neeeophytee/finding-unknowns-skills) into .agents/skills/context-audit in your project. Codex loads it when a task matches its description.
Can I use Context Audit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Neeeophytee/finding-unknowns-skills --skill context-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-audit, .gemini/skills/context-audit, .github/skills/context-audit and .opencode/skills/context-audit in your project.
What does Context Audit need to run?
SKILL.md names no scripts, command-line tools or credentials: Context Audit is instructions for the agent only.
Does Context Audit access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Context Audit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Context Audit use?
Context Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Context Audit use?
About 779 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Context Audit?
Skills that share tags, products or a category with Context Audit: Context Engineering (abashev/vfs-s3, 106 stars), Dotagents Standard (getknit/knit, 132 stars), Reconcile Context (Apocrathia/home-assistant-config, 179 stars) and Verify Agent Context (Luligu/matterbridge, 985 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Context Audit?
Neeeophytee (a GitHub user) maintains it in Neeeophytee/finding-unknowns-skills, which has 343 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 28, 2026.
Source: Neeeophytee/finding-unknowns-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.