Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsnpx agentmods add commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-cursorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-cursor)<a href="https://agentmods.dev/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-cursor"><img src="https://agentmods.dev/badge/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-cursor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-cursor"><img src="https://agentmods.dev/badge/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-cursor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00015 | $0.00555 |
| Opus 5.5 | $0.00006 | $0.00222 |
| Sonnet 5.5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
goal-cursor scanned grade A with 0 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/goal-cursor
1. PURPOSE
Cursor's sessionStart hook receives a native session_id and injects that session's bound packet goal. Cursor's prompt-command surface does not expose the same identity, so anything that binds or mutates a session goal is unsupported here. One thing needs no session: reading a packet's goal.md, which is a file in the repository. That read is allowed.
2. CONTRACT
Inputs: $ARGUMENTS
packet <packet-path>: print the packet's durable slice, frontmatter excluded, with its hash and size.packet-log <packet-path> <item> | <state> | <evidence>: append one progress row below the packet's log anchor through the locked append. A file write that needs no session.- Anything else:
STATUS=FAIL ACTION=<action> ERROR="Cursor command lacks native session identity"andcode=UNSUPPORTED_SESSION_BINDING.
3. INSTRUCTIONS
- If the first token of
$ARGUMENTSispacketorpacket-logand a path follows, run (substituting the action and, forpacket-log, the quoted row):
node .skilled/hooks/goal/bin/goal.cjs packet <packet-path> --runtime cursor --session command-surface --workspace "$PWD"
Print the envelope verbatim. The chat_slice field is the text an operator sets; it never carries frontmatter.
- For any other action, do not run tools or mutate goal state. Print:
STATUS=FAIL ACTION=<action> ERROR="Cursor command lacks native session identity"
code=UNSUPPORTED_SESSION_BINDING
Explain that Cursor injection is session-scoped, that the bound packet goal is injected at session start, and that binding or setting must happen on a runtime whose command surface carries the session identity.
4. HARD RULES
- Do not edit
.skilled/skills/.state/goaldirectly. - Do not call
bin/goal.cjswith a session action from this command;packetreads a file andpacket-logappends one row, and neither binds anything. - Do not run shell commands derived from the goal objective.
- Do not claim that
$ARGUMENTScarries the current Cursor session id.
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.
- 1mo ago Changed 5c6d5914b1fb
- 1mo ago Changed · +10 lines · +1 tokens per session bb9473df27e5
- 2mo ago First seen · 40 lines · 14 tokens per session scan A d6858381ae78
goal-cursor is a command published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (40 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 555 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
goal-cursor compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| goal-cursorMichelKerkmeester/skilled-agent-harness_spec-driven-loops | Command | 40 | yesterday | MIT | A | 15 | Claude Code, Cursor |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |