call-agent
Skill4 starsChanged 4 months agoMITView on GitHub
OPTIONAL (requires a Quarktex API key). Invoke one remote Quarktex agent over the relay — preflight the brain's digests in, build the payload from the agent card's example_prompt, POST /agents/call, handle the needs_input human-in-the-loop on the SAME session_id, then route any returned fact through cite-or-refuse as an attributed third-party claim (sourced into sources/agents/ with the session_id as its citation, then captured to wiki/). Trigger on "call agent X", "ask the <capability> agent", "use the Hive". Only runs when quarktex.enabled:true.
- Reads credentials
3 other projects use a version of this.
Adopted by
Most recently taken up by
- cskwork/call-agenttheir own version, first seen Oct 15, 2026
- cskwork/skillstheir own version, first seen Oct 9, 2026
- Codagent-AI/agent-skillstheir own version, first seen Apr 25, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Codagent-AI/agent-skills★ 31same name
- cskwork/skills★ 3same name
- cskwork/call-agent★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- agents-syncSkill
- captureSkill
- context-restoreSkill
- context-saveSkill
- curatorSkill
- learnSkill
- onboardSkill
- recallSkill
- reviewSkill
- skillifySkill
- wiki-doctorSkill
- worklog-audioSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 0 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read config.yml → require quarktex.enabled: true and a non-empty QUARKTEX_API_KEY in .env (verify with bash integrations/quarktex/relay.sh …
- Very specific: line 16
If either is missing, refuse in one line and stop: *"Quarktex is off — enable it and add a key per integrations/quarktex/SETUP.md."* Do not …
- Very specific: line 28
If the user named a qt_<8> id, use it.
- Very specific: line 31
Check the agent's trust tier (in the cache / connections.md).
- Very specific: line 41
Read the chosen card's example_prompt / example_output — that is the exact payload *shape*.
- Very specific: line 52
Read the response: { success, session_id, turn_number, response, meta }.
- Very specific: line 56
If response.output.status === "needs_input", present output.ask to the user, collect the answer, and
- Very specific: line 65
Write the verbatim exchange to sources/agents/<target_agent_id>-<session_id>.md: the request payload you sent and the final response you …
- Very specific: line 72
Run /capture against sources/agents/<…>.md.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OPTIONAL — requires a Quarktex API key in config.yml; refuse with a one-line setup pointer if disabled.
Inherits
references/kernel.md(the provenance contract). Readsreferences/wiki-spec.mdfor schema. Wire contract:integrations/quarktex/relay-contract.md. Layer overview:integrations/quarktex/README.md.
Gate (check first, every run)
- Read
config.yml→ requirequarktex.enabled: trueand a non-emptyQUARKTEX_API_KEYin.env(verify withbash integrations/quarktex/relay.sh check). - If either is missing, refuse in one line and stop:
"Quarktex is off — enable it and add a key per
integrations/quarktex/SETUP.md." Do not partially run.
What this does
Calls one remote agent on the Quarktex Hive and folds its answer back into the brain only through
the provenance gate. A remote agent is a third-party brain (see the 3-brain separation in
references/kernel.md) — its output is never canon by itself, only ever an attributed, sourced claim.
Execution
Step 1 — Pick the target agent
- If the user named a
qt_<8>id, use it. Otherwise find one: prefer the cacheintegrations/quarktex/agents/_agents.md; if nothing fits, run/agents-sync "<capability>"(orbash integrations/quarktex/relay.sh search "<text>" --capability <cap>) and pick the best card. - Check the agent's trust tier (in the cache /
connections.md).deny→ refuse, full stop.read-only(the default) → you may capture its output as a sourced claim but grant it no write authority.read-write→ its sourced output may auto-route through/capture.
Step 2 — Preflight (digests in)
- Load
digests/(product.md,goals.md,user-profile.md, relevantrecent-decisions.md). Fold the already-known context into the payload so you don't ask the agent what the brain already knows — and so a "prior X applied" is legible. Never paste secrets or.envcontents into a payload.
Step 3 — Build the payload from the card
- Read the chosen card's
example_prompt/example_output— that is the exact payload shape. Buildpayloadto match it (same keys, same structure), filling in the user's real request + preflight context. Don't invent fields the card doesn't show.
Step 4 — Call the relay
- Start with
session_id: null:
(Or, if your brain speaks MCP, call thebash integrations/quarktex/relay.sh call --target qt_yyyyyyyy --payload '<json>'quarktex_call_agenttool — seeintegrations/quarktex/SETUP.md§4.) The brain calls from its caller-onlyfrom_agent_id(no inbound surface). - Read the response:
{ success, session_id, turn_number, response, meta }. Keep thesession_id— it is the citation anchor and the key to continuing the conversation.
Step 5 — Human-in-the-loop (needs_input)
- If
response.output.status === "needs_input", presentoutput.askto the user, collect the answer, and call again with the SAMEsession_id:
Loop until the response is final (nobash integrations/quarktex/relay.sh call --target qt_yyyyyyyy --session ses_xxx --payload '<json>'needs_input). Remember sessions expire after 30 min idle or 50 turns — don't try to resume a cold one.
Step 6 — Land the source (the citation)
- Write the verbatim exchange to
sources/agents/<target_agent_id>-<session_id>.md: the request payload you sent and the finalresponseyou got back. This is the bottom of the provenance chain for this claim. - Hash it (
shasum -a 256 <file> | cut -c1-12) and add a row tosources/_sources.mdwithorigin = quarktex:<target_agent_id> session:<session_id>, <date>. Thesession_idis what makes the claim verifiable — it ties back to a logged, replayable relay call.
Step 7 — Route through cite-or-refuse (hand to /capture)
- Run
/captureagainstsources/agents/<…>.md. Each atomic claim becomes awiki/note that is:type: reference(orfact),confidence: reported,origin: agent-generated,- bodied as an attributed third-party claim — "per {{Agent Name}} (Quarktex), as of
<date>: …", - with a
srcblock whosequoteis a verbatim substring of the saved exchange and whosesourcekey is the new_sources.mdrow.
- Anything worth keeping but not cleanly sourceable →
inbox/withstatus: needs-source. Junk (transient errors, the agent's own unverified beliefs, env-specific noise) → dropped perreferences/blocklist.md. - Close with a one-screen summary: agent + session_id, source file written, N notes captured, M quarantined.
Guardrails (hard)
- Autonomy never bypasses governance. A relay response enters canon ONLY via cite-or-refuse. A
read-onlyagent gets no write authority; adenyagent is never called. - The source is the exchange, not the brain's paraphrase. Quote the saved
sources/agents/file verbatim; never cite awiki/note as the source of a relay claim. - Never leak secrets into a payload (no
.env, no keys, no PII the user didn't authorize sending out). - Empty /
success:false/ timeout → no source, nowiki/write. Report it honestly; at most aninbox/draft noting the attempt. Never fabricate a response to fill the gap. - Caller-only. The brain calls; it never registers a webhook or runs an agent locally.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

