agent-context-budget SKILL.md skillA
agent-context-budget from wenyuchiou/agent-collab-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wenyuchiou/agent-collab-skills/agent-context-budget@git:20261016.a802ce4Pins git:20261016.a802ce4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wenyuchiou/agent-collab-skills
- Path
skills/agent-context-budget/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261016.a802ce4, committed Oct 16, 2026
- First version recorded
- May 14, 2026
- Size
- 6,297 bytes
- Repository stars
- 32
- License
- MIT
Use when launching parallel or background subagents, or when a handoff, log, or result would be more than a short summary (roughly 2 KB). Caps return sizes (summary in the reply, detail by path), picks a cheap model tier for mechanical lanes, records durable decisions as proposals, and checkpoints or primes a fresh session before context runs out.
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
# agent-context-budget Keep the primary session small while lanes do the reading and writing. There is no second budget source: native mode follows the host's limits and the caps written into each brief; harness mode takes every number from the policy referenced by the current `TaskCheckpoint`. The "roughly 2 KB" in the description says when to use this skill; it is not a limit. Do not use this skill to summarize away unresolved failures, human decisions, raw scientific evidence, or security findings. ## Before launching lanes - Put a return cap in every brief: status, short summary, files changed, checks run, risks, blockers. Long output goes to a file and the lane returns the path. Raw logs, transcripts, and full diffs never come back inline. - Reading lanes return conclusions with `file:line` references, not file dumps. Name exact files and line ranges in the brief. - Choose model tiers before launch: a cheap tier for mechanical lanes (pattern edits, scaffolds, bulk reads), a strong tier for review, verdicts, root-cause analysis, security, and governance. Never switch a lane's model silently after a failure. …
Read the whole file at its exact version.
How to install
mdr add wenyuchiou/agent-collab-skills/agent-context-budget@sha256:4eadc620eec888fcThe line at the top of this page pins the label git:20261016.a802ce4, 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_nivmn2diuyhig4ex)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 14, 2026 and Oct 16, 2026, about one every 39 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261016.a802ce4 latest | 2026-10-16 | a802ce4 | 6,297 B | A | view · diff |
| git:20260904.4e8a7fd | 2026-09-04 | 4e8a7fd | 4,917 B | A | view · diff |
| git:20260904.e7df8fd | 2026-09-04 | e7df8fd | 4,296 B | A | view · diff |
| git:20260831.ca20117 | 2026-08-31 | ca20117 | 3,811 B | A | view · diff |
| git:20260514.1a5ac90 | 2026-05-14 | 1a5ac90 | 6,157 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 (6297 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
wenyuchiou/agent-collab-skills · 32 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nivmn2diuyhig4ex GET https://markdownregistry.com/api/v1/resolve?ref=wenyuchiou/agent-collab-skills/agent-context-budget GET https://markdownregistry.com/api/v1/blob/4eadc620eec888fc7761c047d506d987a0bd94edeac11a324cc1cf8834b06f17
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.