token-budget SKILL.md skillA
token-budget from byerlikaya/claude-starter-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add byerlikaya/claude-starter-kit/token-budget@git:20260929.b7001cdPins git:20260929.b7001cd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- byerlikaya/claude-starter-kit
- Path
kit/skills/token-budget/SKILL.md- Versions recorded
- 6
- Latest version
- git:20260929.b7001cd, committed Sep 29, 2026
- First version recorded
- Sep 24, 2026
- Size
- 4,887 bytes
- Repository stars
- 26
- License
- MIT
Context/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Token & Context Discipline <!-- routing-eval reads the next line; why it sits in the body: AGENT_TEMPLATE.md --> Trigger phrases: "token budget", "token cost", "context window", "context management", "context is full", "clear context", "running out of context" A subagent exists for context management: it runs in its own window and returns **only its summary** to the main thread — intermediate noise (file reads, searches, logs) never enters the main context. **Warning — measured, not guessed.** Each subagent re-pays its **full context from scratch**: in a real transcript the first turn was `cache_read=0`, every token `cache_creation` — nothing is shared with the main thread's cache. A **no-op** subagent (task = "reply DONE") already cost **~10k tokens with restricted tools and ~16k with full tool access**; that floor is base system prompt + tool schemas, paid fresh every time. Of the always-on material only the **skill listing (~2.5–3k tokens) is inherited** by a subagent — the discipline (`DISCIPLINE.md`/CLAUDE.md) and the agent descriptions are **not** injected into it. So a delegation is worth it …
Read the whole file at its exact version.
How to install
mdr add byerlikaya/claude-starter-kit/token-budget@sha256:5ee282bfb6d4bf83The line at the top of this page pins the label git:20260929.b7001cd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ztgjofusqih5czdo)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Sep 24, 2026 and Sep 29, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260929.b7001cd latest | 2026-09-29 | b7001cd | 4,887 B | A | view · diff |
| git:20260926.aaa5dbc | 2026-09-26 | aaa5dbc | 4,810 B | A | view · diff |
| git:20260925.68939f0 | 2026-09-25 | 68939f0 | 4,804 B | A | view · diff |
| git:20260924.a457823 | 2026-09-24 | a457823 | 4,802 B | A | view · diff |
| git:20260924.ccb2bc9 | 2026-09-24 | ccb2bc9 | 4,936 B | A | view · diff |
| git:20260924.bd59e95 | 2026-09-24 | bd59e95 | 4,936 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4887 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
byerlikaya/claude-starter-kit · 26 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ztgjofusqih5czdo GET https://markdownregistry.com/api/v1/resolve?ref=byerlikaya/claude-starter-kit/token-budget GET https://markdownregistry.com/api/v1/blob/5ee282bfb6d4bf83a81ce2861d532ccfc80b1e4bea72a2211cb2e921b22e0eae
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from byerlikaya/claude-starter-kit
Every file in byerlikaya/claude-starter-kit