db-access-review-subagent-needs-explicit-probe-budget SKILL.md skillA
db-access-review-subagent-needs-explicit-probe-budget from wan-huiyan/agent-traffic-control is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wan-huiyan/agent-traffic-control/db-access-review-subagent-needs-explicit-probe-budget@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wan-huiyan/agent-traffic-control
- Path
plugins/agent-traffic-control/skills/db-access-review-subagent-needs-explicit-probe-budget/SKILL.md- Versions recorded
- 8
- Latest version
- v1.1.0, committed Sep 17, 2026
- First version recorded
- Jun 1, 2026
- Size
- 7,519 bytes
- Repository stars
- 3
- License
- MIT
Dispatching a review or verification agent with live database, gcloud, psql or bash access: give it a tool call and time budget, plus the probes NOT to re-run. Also when it gives `API Error: The socket connection was closed unexpectedly`, or has run 30 minutes. Not its sources.
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
# A review subagent with live-DB access needs an explicit probe budget ## Problem You dispatch a `general-purpose` subagent to review a PR or verify findings, and it has live database / cloud / Bash access. Unprompted, it does the thorough thing: re-derives every claim from scratch, running expensive exploratory queries (full-window joins, multi-date sweeps, dry-runs). Two failure modes follow: 1. **It runs very long** (20–40+ min of wall time on heavy probes), far past what the review needs. 2. **It can socket-close mid-run.** The Agent tool returns `API Error: The socket connection was closed unexpectedly` with a non-zero `tool_uses` count but **no final assistant message** — so the agent did real work (11, 20 tool calls) but its **verdict was never delivered**. The output is lost, and it is **not resumable** from the orchestrator unless a `SendMessage`/continue tool is available (often it is not). You've burned the tokens and the wall-clock for nothing. The root cause is that an unbounded reviewer treats "review this change" as "independently re-establish the entire ground truth," which is exactly the slow, fragile thing — when the orchestrator has usually …
Read the whole file at its exact version.
How to install
mdr add wan-huiyan/agent-traffic-control/db-access-review-subagent-needs-explicit-probe-budget@sha256:aeaf4c131489aacdThe line at the top of this page pins the label v1.1.0, 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_yri2w3it2hz6d7nu)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Jun 1, 2026 and Sep 17, 2026, about one every 15 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-09-17 | adfab38 | 7,519 B | A | view · diff |
| v1.0.1 | 2026-09-17 | 123b707 | 7,159 B | A | view · diff |
| v1.0.1 | 2026-09-17 | da7c1a6 | 6,773 B | A | view · diff |
| v1.0.1 | 2026-09-02 | a0dbbfd | 6,464 B | A | view · diff |
| v1.0.0 | 2026-08-10 | 5b6d8a2 | 6,153 B | A | view · diff |
| v1.0.0 | 2026-08-10 | a58c34c | 6,133 B | A | view · diff |
| v1.0.0 | 2026-08-10 | a39e221 | 7,266 B | A | view · diff |
| v1.0.0 | 2026-06-01 | c0293a0 | 6,151 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 (7519 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
wan-huiyan/agent-traffic-control · 3 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yri2w3it2hz6d7nu GET https://markdownregistry.com/api/v1/resolve?ref=wan-huiyan/agent-traffic-control/db-access-review-subagent-needs-explicit-probe-budget GET https://markdownregistry.com/api/v1/blob/aeaf4c131489aacd5c8a003730561056300d5c32b4df749f2911c33b97fe204b
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.