render-loop SKILL.md skillB
render-loop from y-a-v-a/session-export is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add y-a-v-a/session-export/render-loop@git:20261107.a2e3ef4Pins git:20261107.a2e3ef4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- y-a-v-a/session-export
- Path
.claude/skills/render-loop/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261107.a2e3ef4, committed Nov 7, 2026
- First version recorded
- Jun 19, 2026
- Size
- 4,585 bytes
- Repository stars
- 3
- License
- MIT
Project-local dev feedback loop for the session-export renderer. Use when asked to check, fix, or improve how a Claude Code / Codex session renders in the exported HTML — e.g. "check the rendering of tool call X around Y, see session <uuid>". Exports the session to HTML, screenshots the relevant card with headless Chrome so the result can be viewed, then guides editing skills/session-export and re-validating.
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
# render-loop A self-checking loop for developing this repo's exporter. It lets you **see** what the HTML actually renders (via a headless-Chrome screenshot you can open with the Read tool), fix the renderer, and re-validate — without leaving the session. This skill is repo-local (`.claude/skills/render-loop/`) and not shareable: it hard-codes this repo's layout (`skills/session-export/`) and assumes Google Chrome + Node 18+. ## The loop When the user points at a rendering concern and a session (e.g. *"the rendering of TaskGet looks like raw JSON, see session 2e875f45…"*): 1. **Locate & classify the session.** A session id is a UUID. Claude sessions live under `~/.claude/projects/**/<uuid>.jsonl`; Codex rollouts under `~/.codex/sessions/**/rollout-*<uuid>*.jsonl`. If it's a Codex rollout, use `--codex`. You can pass a full path instead of an id. 2. **Inspect the raw record first.** Find the relevant `tool_use` / message in the jsonl to learn the exact input/result shape before changing code: ``` grep -n '"name":"TaskGet"' <session.jsonl> # or node one-liner to dump the block ``` 3. **Export + screenshot the card.** From the repo root: ``` …
Read the whole file at its exact version.
How to install
mdr add y-a-v-a/session-export/render-loop@sha256:583bf2fec81d3af1The line at the top of this page pins the label git:20261107.a2e3ef4, 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_xhaqjd3scfa24eww)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jun 19, 2026 and Nov 7, 2026, about one every 141 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261107.a2e3ef4 latest | 2026-11-07 | a2e3ef4 | 4,585 B | B | view · diff |
| git:20260619.4d35995 | 2026-06-19 | 4d35995 | 4,044 B | B | view |
Audit of the latest version
- fail: No script tag (matched: <script)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4585 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
y-a-v-a/session-export · 3 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xhaqjd3scfa24eww GET https://markdownregistry.com/api/v1/resolve?ref=y-a-v-a/session-export/render-loop GET https://markdownregistry.com/api/v1/blob/583bf2fec81d3af12178abd188962d28efc0e1cc16feeac2176d78a7d67cd16a
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.