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 commands/ashlrai/ashlr-plugin/goalgit clone --depth 1 https://github.com/ashlrai/ashlr-pluginWrote 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/ashlrai/ashlr-plugin/goal)<a href="https://agentmods.dev/commands/ashlrai/ashlr-plugin/goal"><img src="https://agentmods.dev/badge/commands/ashlrai/ashlr-plugin/goal.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00482 |
| Opus 5 | $0.00013 | $0.00241 |
| Sonnet 5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
goal 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 4d 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.
What it actually says
Registers an objective with the ashlr fleet, plans it into milestones, and runs
the next one sandboxed — filing a PENDING inbox proposal. Nothing is applied
until you review and accept via ashlr inbox.
Usage
/goal "<objective>" [--project <repo>] [--allow-cloud] [--plan-only] [--direct]
Flags:
--project <repo>— target repo path (required with--direct; optional otherwise)--allow-cloud— permit cloud-tier backends for the sandboxed run--plan-only— stop after milestone planning; do not advance yet--direct— skip milestone decomposition; run the objective verbatim as a single sandboxed frontier-engine run (same dispatch path as the daemon). Requires--project.
Steps
If $ARGUMENTS is empty
Print the following and stop:
Usage: ashlr goal "<objective>" [--project <repo>] [--allow-cloud] [--plan-only] [--direct]
Create a goal, plan it into milestones, and advance the next one as a
sandboxed, PROPOSAL-ONLY run (review it via `ashlr inbox`). Routed across
the polyglot backend roster by capability + trust tier.
--direct Skip milestone decomposition. Run the objective verbatim as a
SINGLE sandboxed proposal-only frontier-engine run (same path as
the daemon's non-builtin dispatch). Requires --project.
Ideal for concrete tasks that need no Design->Implement->Test split.
Otherwise
Run the following Bash command and relay its output verbatim:
ashlr goal $ARGUMENTS
After the command completes, if a proposal ID appears in the output, relay it and add exactly one reminder line:
Review the proposal with
ashlr inbox— nothing was applied to the working tree.
No preamble, no trailing summary beyond the above reminder.
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.
- 4d ago First seen · 59 lines · 25 tokens per session scan A 7858599532ab
goal is a command published in the GitHub repository ashlrai/ashlr-plugin (3 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 482 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
upgrade-webkit
Upgrade Bun's WebKit fork to the latest upstream version of WebKit.
dedupe
Find duplicate GitHub issues.
rp-build-cli
Build with rp-cli context builder → chat → implement.
scriptwriter-draw
Draw a random chaos card from the 13-card deck — a plot-twist prompt the user can use as a scene seed, a basistext for an RRR cascade, or a riff for a room contribution.
specsync-create-spec
Create a new spec-sync module spec.
nimbus-embedding-routing
Hybrid 384/1536-dim embedding routing (Phase 5 T6 PR 3): PROSEHEAVYTYPES, EMBEDDINGDIMLOCAL/EMBEDDINGDIMOPENAI, the RoutingEmbeddingPipeline wrapper, dual-table search (vecitems384 + vecitems1536 via vectorSearchChunksDual), the V30 migration (1536-dim table + dim-aware delete triggers), the nimbus index reembed CLI +…