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/iolairus/borderlint/task-generategit clone --depth 1 https://github.com/iolairus/borderlintWhat 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 | $0.00017 | $0.00405 |
| Opus 5 | $0.00009 | $0.00202 |
| Sonnet 5 | $0.00003 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
task-generate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Generate tasks from the discovery doc backlog/discovery/$ARGUMENTS.md using templates/task.md.
Steps
-
Read the discovery doc. If it doesn't exist, list available ones and ask which to use (or suggest
/req-capturefirst).Tasks are written in English (the repo's only content language); each task's frontmatter records
language: en. -
Read
workflow.yaml(jira.project_key,backlog.tasks_dir). -
Slice the functional needs into tasks. Rules:
- One verifiable outcome per task; split anything you couldn't implement in one OpenSpec change.
- Each task gets a Goal (what & why), Context, and at least one Gherkin scenario per acceptance criterion, including one unhappy path. Every Then must be observable/testable.
- Non-functional needs become acceptance criteria on the tasks they constrain, or their own task if cross-cutting.
- Do NOT create tasks from Open questions — list them at the end as "blocked: needs answer".
-
Task IDs are Jira keys. Show the user the proposed task list (title + one-line goal) and ask them to provide the Jira ID for each (e.g.
PROJ-123). For tasks not yet created in Jira, assign draft IDs<project_key>-D01,-D02, ... and note they must be renamed when the real key exists. -
Write each task to
backlog/tasks/<id>-<slug>.mdwith frontmatter filled:id,title,status: draft,discovery,priority(MoSCoW from the discovery's goals),language. -
Suggest
/task-enrich <id>for the ones to refine, or/task-jira <id>to export.
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.
- 2d ago First seen · 26 lines · 17 tokens per session scan A 40f97990b0c7
task-generate is a command published in the GitHub repository iolairus/borderlint (7 stars, last pushed 9d ago), licensed MIT. It adds 17 tokens to every session and 405 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
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
new
Creates a new item in a module that supports the new capability.
card
Open one self-contained OverClick card.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.