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/Elnora-AI/elnora-linearWrote 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/elnora-ai/elnora-linear/linear-curator-run)<a href="https://agentmods.dev/commands/elnora-ai/elnora-linear/linear-curator-run"><img src="https://agentmods.dev/badge/commands/elnora-ai/elnora-linear/linear-curator-run/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/elnora-ai/elnora-linear/linear-curator-run"><img src="https://agentmods.dev/badge/commands/elnora-ai/elnora-linear/linear-curator-run.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 | $0.00017 | $0.00301 |
| Opus 5.5 | $0.00007 | $0.00120 |
| Sonnet 5.5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
linear-curator-run 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.
What it actually says
Linear Curator (collect + report)
Collect signals from the signal sources configured in references/signal-sources.json. This is the diagnostic half of the curator — it tells you what each source is seeing. The rule engine (which turns signals into proposed issue mutations) ships in a follow-up release.
Run
All configured sources:
elnora-linear curator-run --output text
A specific source by name:
elnora-linear curator-run --source "ci-failing-tests"
What it reports
For each enabled source:
[ok] <name> (<type>): N signal(s)plus the first 10 payloads[!!] <name> (<type>) — error: <message>if the source failed (the others keep running)
Supported source types
external_command— runs any shell command, parses stdout as JSON or linesgithub_commits,github_pr,slack_messages,linear_issues,mcp_tool— declared in the schema; not yet implemented (they'll surface as errors)
Don't
- Don't expect mutations from this command — it's collect-only in v0
- Don't configure
external_commandsources that run untrusted scripts — the command runs with the user's full privileges
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 First seen · 40 lines · 17 tokens per session scan A bdff5db2451f
linear-curator-run is a command published in the GitHub repository Elnora-AI/elnora-linear (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 17 tokens to every session and 301 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 2026-08-31.
Other commands, from other repositories
trekker:task-agent
Autonomous agent that finds ready work and completes it.
trekker:history
View audit log of changes to understand what happened in past sessions.
trekker:list
List tasks with optional filters.
trekker:start
Begin working on a task by setting its status to inprogress.
trekker:create
Create a new task interactively.
trekker:blocked
Mark a task as blocked when it cannot proceed.