← Search

Context Budget
AI Productivity 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit 4eb71d9
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: Claude Code or Codex…

Context Budget

Context budget answers without the scan: your harness's live meter by default (/context in Claude Code, /status in Codex); a bounded, read-only component audit only on explicit --audit.

At a glance
What
Context budget answers without the scan: your harness's live meter by default (/context in Claude Code, /status in Codex); a bounded, read-only component audit only on explicit --audit.
Cost
Free
Needs
Claude Code or Codex; nothing else — no accounts or keys required.
Level
Beginner — Claude Code or Codex…
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

Quick answer

Context Budget is a free Muse skill that answers questions about your Claude Code or Codex context window without scanning anything by default. Ask about your budget and it points you to the built-in meter, /context in Claude Code or /status in Codex, and explains what it shows. A bounded audit runs only on an explicit flag.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 4eb71d9

Before you start: tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead. Prerequisites: Claude Code or Codex; nothing else — no accounts or keys required. Install "Context Budget" for me. Context Budget answers questions about how much room is left in my session's context window. By default it does not scan anything: it simply points me to my harness's built-in meter — /context in Claude Code (/context all for the expanded breakdown), /status in Codex — and explains what it shows. A static audit of my installed components exists, but only as an explicit opt-in: I have to ask for it with --audit (or say "audit installed components"). The audit is read-only and bounded: it looks only at the install root and configuration files I name, only at component descriptions and metadata (not full skill or agent bodies), caps its inventory at 50 entries per kind, and reports estimated eager overhead by component class with the heaviest entries and up to three optimizations. Every number it gives is an estimate of static configuration overhead, never a live session measurement. There is also an optional diagnostic for a single session log file, only when I explicitly pick that file. Source: https://raw.githubusercontent.com/affaan-m/ECC/4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2/skills/context-budget/SKILL.md (the skill is the single SKILL.md file in the skills/context-budget folder of the affaan-m/ECC repository) Pinned version: install the code at commit 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated October 12, 2026: Skill Harbor regenerated this install prompt from the current upstream file. What changed for you: the skill no longer audits your setup by default. The previous version scanned your component folders and produced a token-cost inventory whenever you asked about your context budget; the new version refuses that scan unless you explicitly opt in with --audit, and otherwise just tells you the native command (/context in Claude Code, /status in Codex) that shows your live usage. The audit itself is narrower than before: read-only, limited to the scope you name, metadata only, capped at 50 entries per kind. The previous prompt told your agent to audit your context budget and flag the bloat — that instruction is now refused by default. 1. Download the SKILL.md file into a temporary folder. 2. Compare the file with the fingerprint from Skill Harbor's review of 2026-10-12: - SKILL.md: SHA-256 793d51ac6639a466213800c228189a48b102c88d7cfb5b0651baa3480a577206 If it does not match, the file changed since the review: do not install it yet — tell me what you found and let me decide. 3. Read the file and tell me in plain words: what the skill does when used, whether it connects to a service, whether it reads or sends any personal information or keys, and anything that seems unusual. 4. When I say yes, copy SKILL.md into my skills folder, in a folder named "context-budget". 5. Check the copy opens correctly (valid frontmatter, files in place) and tell me what was installed, where, and what is left for me to do (for example, ask about my context budget in a session to get the native command, and remember the static audit only runs if I explicitly say --audit). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: only touch the temporary folder and the install target. If something seems off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 4eb71d9 · 2026-10-13
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : no network contact
🔎 Last checked · Nov 21, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
4eb71d9 · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 21, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.