Cursor + tman

The hook can allow, ask, or deny — but not rewrite. tman still decides whether the command runs; getting it supervised takes a shim or a denial the model can act on.

vendor: Anysphere
integration: gates
hook event: beforeShellExecution
config: hooks.json

Cursor fires beforeShellExecution before the agent runs any shell command, and the response controls permission — allow, ask, or deny, with messages for the user and for the model. It does not carry a replacement command. So supervision here is two mechanisms working together: shims that catch the command silently, and a denial that catches what the shims cannot.

1. Install tman and adopt the project

Everything below assumes the binary is on your PATH and the repository has a .tman.kdl. That file is what scopes caps to this project, and it is also the signal several of the integrations test for before they do anything.

shell

npm install -g @standardbeagle/tman   # or the install.sh one-liner

cd your-project
tman init --shims --gitignore

tman init writes a defaults block and an alias for each test or build command it can detect. Commands it cannot detect are left commented out rather than stubbed, so an alias you never filled in fails loudly instead of exiting 0 having run nothing.

For Cursor the shims are the load-bearing half. A shell command the agent issues resolves ./test through the repository root, and that file is already a supervised entry point — no hook involved.

Turn the rewrite into an actionable denial

Because this hook cannot replace the command, the useful move is to refuse the unsupervised one and hand the model the supervised string to re-issue. tman already knows which commands deserve that and what the replacement should be, so the adapter is a few lines around tman hook pretooluse rather than a second copy of the classifier.

~/.config/tman-gate.sh — chmod +x

#!/usr/bin/env bash
# tman-gate.sh — deny an unsupervised test/build command, naming its supervised form.
set -euo pipefail
payload=$(cat)

# .command // .tool_input.command // empty
command=$(jq -r '.command // .tool_input.command // empty' <<<"$payload")
[ -n "$command" ] && [ "$command" != "null" ] || exit 0

verdict=$(jq -nc --arg c "$command" --arg d "$PWD" \
  '{tool_name:"Bash", cwd:$d, tool_input:{command:$c}}' | tman hook pretooluse)

# tman stays silent on anything it will not supervise. So does this.
[ -n "$verdict" ] || exit 0
supervised=$(jq -r '.hookSpecificOutput.updatedInput.command // empty' <<<"$verdict")
[ -n "$supervised" ] || exit 0

jq -nc --arg s "$supervised" '{
  permissionDecision: "deny",
  permissionDecisionReason: ("Run it supervised instead: " + $s)
}'

Confirm the payload field before you trust it. Hook payload shapes move between versions, and a jq path that no longer matches yields an empty command and a script that silently allows everything — a false green. Replace the script with cat > /tmp/hook-payload.json for one run, read the file, then wire the real adapter against the field name you actually saw.

Register the hook

hooks.json

{
  "version": 1,
  "hooks": {
    "beforeShellExecution": [
      { "command": "~/.config/tman-gate.sh" }
    ]
  }
}

A deny is a real interruption, unlike a rewrite. Keep the adapter narrow — it only denies commands tman itself classifies as supervisable test or build work in an adopted project — and prefer "ask" over "deny" while you are still calibrating, so a false positive costs a keystroke rather than a stalled agent.

Tell the model, in AGENTS.md

Shims and hooks catch the mechanical cases. The remaining gap is the model deciding to do something clever — running the suite through a subshell, or with an inline environment assignment, both of which tman deliberately refuses to rewrite because prefixing a string it did not parse changes what runs. A standing instruction in AGENTS.md closes that gap:

AGENTS.md

## Running tests and builds

Run every test, build, lint, and typecheck command through tman — never bare.
Prefer the repo-root shims (`./test`, `./lint`) when they exist; they carry
this project's `.tman.kdl` caps. Otherwise prefix explicitly:

    tman run -- <command>

Never widen the caps from the command line. Exit 124 is a timeout, 125 a stall,
126 a resource cull — report those, do not retry with looser limits.

Verify it is actually on

A supervision integration that silently does nothing is worse than none, because it stops you looking. Two checks, both of which fail visibly:

shell

# 1. the classifier agrees this command is worth supervising
echo '{"tool_name":"Bash","cwd":"'"$PWD"'","tool_input":{"command":"npm test"}}' \
  | tman hook pretooluse

# 2. a real run shows up while it is in flight
tman run --name smoke -- sleep 30 &
tman list

The first prints a JSON object naming the rewritten command. Empty output means tman decided to stay out of the way — no .tman.kdl above cwd, a command it does not classify as test or build work, or a shell string it refused to parse. The second must list the run; if tman list is empty, nothing is being supervised.

Caps worth setting for agent-driven work

An agent re-runs the same command far more often than a human does, and it does it while you are not watching. That changes which caps earn their keep:

cap	why it matters more under an agent
`--name`	The agent will start the suite again before the last one finished. A dedup lock refuses the duplicate instead of running two copies against the same port or database.
`--max-parallel 2`	The default, and the right one for most repos. Excess runs queue on a slot file rather than stampeding your cores.
`--max-time`	The only cap that bounds a run which is genuinely working but will never finish — a wait on a peer that never answers looks identical to healthy IO.
`--stall 30m`	The built-in. A hang backstop, not a runtime budget: it should sit well above the longest quiet stretch your slowest command legitimately has.
`--max-mem`	Opt-in, and worth it where a leak mode exists — worker pools, browser fleets, long-lived daemons. Off by default because builds are supposed to be greedy.

Per-command starting points live in the tuning guides — one page per test and lint tool, with the reasoning behind each number rather than just the number.

Frequently asked

Can Cursor's hooks rewrite a shell command before it runs?

No. `beforeShellExecution` returns a permission decision — allow, ask, or deny — plus optional messages for the user and the agent. Getting a command supervised therefore takes either a PATH shim, which the agent resolves without knowing, or a denial that names the supervised form for the model to re-issue.

Will the deny adapter block ordinary commands?

Only what tman classifies as test or build work in a project that has a .tman.kdl. Anything else — git, a dev server, a one-off script — produces no verdict from `tman hook pretooluse`, and the adapter exits without printing, which Cursor reads as allow.

Other agents

Sources

Vendor documentation this guide is written against — hook surfaces move, so check yours if something below does not match what you see.