Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/7xuanlu/wenlan/setupnpx skills add 7xuanlu/wenlan --skill setupgit clone --depth 1 https://github.com/7xuanlu/wenlanWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00059 | $0.01794 |
| Opus 5 | $0.00030 | $0.00897 |
| Sonnet 5 | $0.00012 | $0.00359 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade C, and why
setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/7xuanlu/wenlan/v${RELEASE_VER}/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS -m 3 http://127.0.0.1:7878/api/health && break How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup
Self-healing setup for Codex. Default backend is local memory: no local model, no API key, no prompt ceremony. Local model and Anthropic key are optional upgrades after the basic path works.
Steps
Run in order. Stop and report at the first failure that needs human attention. Otherwise, push through automatically.
1. Health probe
for i in 1 2 3; do
curl -fsS -m 3 http://127.0.0.1:7878/api/health && break
sleep 1
done
- 200 OK: continue to version drift probe.
- Anything else: continue to bootstrap.
2. Version drift probe
Compare daemon version vs plugin manifest version:
PLUGIN_JSON="${CODEX_PLUGIN_ROOT:-plugin-codex}/.codex-plugin/plugin.json"
[ -r "$PLUGIN_JSON" ] || PLUGIN_JSON=".codex-plugin/plugin.json"
if command -v python3 >/dev/null 2>&1 && [ -r "$PLUGIN_JSON" ]; then
RESP="$(curl -fsS -m 3 http://127.0.0.1:7878/api/health)"
DAEMON_VER="$(printf '%s' "$RESP" | python3 -c 'import json,sys; print(json.load(sys.stdin).get("version",""))')"
EXPECTED_VER="$(python3 -c 'import json,sys; print(json.load(open(sys.argv[1])).get("version",""))' "$PLUGIN_JSON")"
RELEASE_VER="${EXPECTED_VER%%+*}"
printf 'daemon=%s expected=%s release=%s\n' "$DAEMON_VER" "$EXPECTED_VER" "$RELEASE_VER"
else
echo "version_check=skipped"
fi
- Same version: continue to doctor.
- If the probe cannot run because the runtime is down: continue to bootstrap.
- If
PLUGIN_JSONis unreadable orpython3is missing: continue to doctor; Codex will keep using this slice until the plugin cache is updated. - If mismatch, check the direction before repairing. Compare the release part
of
daemon=(strip the+g<sha>suffix) againstrelease=, numeric per component, not lexicographic. Daemon release equal or newer → the plugin cache is stale, not the runtime: skip the repair below (it would only reinstall the same-or-latest runtime and restart a healthy daemon) and go straight to the stop message in step 4 — update the plugin, restart, rerun. - Only if the daemon release is older than the plugin release, repair the runtime:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed 7e4512da4568
- 2d ago First seen · 204 lines · 59 tokens per session scan C 2a3257e44457
setup is a skill published in the GitHub repository 7xuanlu/wenlan (60 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,794 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
forgetful-encode-repo
Encode a repository into the Forgetful knowledge base — bootstrap the project, its entities, memories, and documents from the codebase itself. Use when bringing a new repo under Forgetful or refreshing a stale encoding. Re-encoding is an update pass: query-before-create makes it supersession, not duplication.
odin-close-session
Settle a Muninn at the end of a working session. Use when the user says "close out", "wrap up", "settle the base", "we're done here", or invokes the close-session command while working with an Odin knowledge base. Reviews pending candidates, verifies lint, names anything still parked, and (for a git-backed base)…
odin
Organizational memory. Ingest documents into a durable, provenance-tracked knowledge base (a "Muninn") and reason over it. Use when the user says "remember this", "ingest", "odin ...", pastes or points at a document to save, asks to set up a knowledge base, asks what's known across saved sources, or asks Odin to go…
use-verifiable-memory
Research and synthesize from a local Verifiable Memory Bank with source-backed evidence, reproducible selectors, chronology, attribution, and explicit uncertainty. Use when a request asks Codex to recall banked material, investigate a topic, verify a claim, build a dossier or timeline, distinguish quoted facts from…
verification
Verify agent code against organizational policies and best practices. Trigger this skill when the user says something like "verify my agent", "review agent code", "check compliance", "audit my agent", "check my agent against rules", or "validate agent implementation".
documentation
Searches for relevant documentation. Use to gather details on specific libraries or APIs. Use when you are instructed to use a specific technology, but are not given details about it in the context.