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.
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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-opencode)<a href="https://agentmods.dev/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-opencode"><img src="https://agentmods.dev/badge/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-opencode/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-opencode"><img src="https://agentmods.dev/badge/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/goal-opencode.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 | $0.00006 | $0.01956 |
| Opus 5.5 | $0.00002 | $0.00782 |
| Sonnet 5.5 | $0.00001 | $0.00391 |
| Haiku 4.5 | $0.00001 | $0.00196 |
Grade A, and why
goal-opencode 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 8d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/goal-opencode
Thin root router for the session goal plugin.
1. PURPOSE
Manage the passive session goal through the opencode-goal plugin. /goal-opencode is a state-free router: it resolves the requested action from $ARGUMENTS and dispatches to the opencode_goal / opencode_goal_status plugin tools, which own all goal state and session resolution.
2. ARGUMENT ROUTING
Resolve routing inputs from the command arguments $ARGUMENTS:
QUERY= the full$ARGUMENTSstring, trimmed.ARGS_PRESENT= true whenQUERYis non-empty.FIRST= the first whitespace-delimited token ofQUERY, lowercased.REST=QUERYwith the leadingFIRSTtoken removed, trimmed.
Bind routing to these resolved ARGS_PRESENT, QUERY, FIRST, and REST values.
3. CONTRACT
Inputs: $ARGUMENTS — bind <packet-path> | resent | packet <packet-path> | set <objective> [--budget N] | show | history | doctor | health | clear | complete | pause [reason] | resume
Outputs: STATUS=<OK|FAIL> ACTION=<bind|resent|packet|set|clear|complete|pause|resume|history|doctor|health|show>
This command is state-free. It never reads or writes .skilled/skills/.state/goal directly.
- Empty arguments or
showroute toopencode_goal_status. bind <packet-path>routes toopencode_goalwithaction: "bind"andpacketPath. The packet'sgoal.mdbecomes the directive: the objective is derived from it, the injection renders from the file on every turn, and the frontmatter never leaves the file.unbindroutes toopencode_goalwithaction: "unbind", dropping the packet pointer and keeping the record.resentroutes toopencode_goalwithaction: "resent", recording that the current durable slice was resent in chat so the reminder stops.log <item> | <state> | <evidence>routes toopencode_goalwithaction: "log"and the three parts; the row lands below the packet's log anchor under the per-packet lock and never touches the durable slice.packet <packet-path>routes toopencode_goalwithaction: "packet"andpacketPath: a session-free read of the packet's durable slice, hash and size.set <objective> --budget Nroutes toopencode_goalwithaction: "set",objectivewith the budget suffix removed, andtokenBudget: N. The budget is a recorded reading only and never stops a goal; the reply carries onenotice=line that says so.set <objective>routes toopencode_goalwithaction: "set"andobjective: REST.- Bare text routes to
opencode_goalwithaction: "set"andobjective: QUERY. history,doctor, andhealthroute to read-onlyopencode_goalactions.historyreturnsarchive_countandarchive_N_*fields.doctor/healthreturnactive_state_file_count,archive_file_count, log byte sizes,last_sweep_at, andorphan_candidate_count.clear,complete,resume, andpause [reason]route toopencode_goal.resumealso releases an active goal that an older version suppressed with a retired cap or budget reason.- Any other non-empty
QUERYis treated as bare goal text and routes toopencode_goalwithaction: "set"andobjective: QUERY.
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.
- 8d ago Changed · +2 lines 4a5007a45c4c
- 12d ago Changed 474219b24cd1
- 1mo ago Changed 603fad4374cd
- 1mo ago Changed · +8 lines c66d9f681406
- 2mo ago First seen · 101 lines · 6 tokens per session scan A 9481473d44a9
goal-opencode is a command published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (40 stars, last pushed yesterday), licensed MIT. It adds 6 tokens to every session and 1,956 once invoked, about $0.0000 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-opencode compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| goal-opencodeMichelKerkmeester/skilled-agent-harness_spec-driven-loops | Command | 40 | yesterday | MIT | A | 6 | Claude Code, OpenCode |
| 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 |