task-reviewer

A read-only checker for backlog tasks before they are sent to Jira or used to create OpenSpec changes. It checks whether each task is clear, testable, independent, consistent, and traceable to its source.

In plain words
What is it for?
Use it after generating or enriching tasks to review their goals, Gherkin acceptance tests, links to discovery files, IDs, status, and consistency with related specifications.
Why use it?
It catches vague requirements, missing failure cases, hidden dependencies, and inconsistent task details before they reach planning or tracking tools.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/iolairus/borderlint/task-reviewer
Clone the repo
git clone --depth 1 https://github.com/iolairus/borderlint

Made for: Claude Code.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00315
Opus 5 $0.00023 $0.00158
Sonnet 5 $0.00009 $0.00063
Haiku 4.5 $0.00005 $0.00032

Measured 2d ago against content hash 097eaa57b162, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-reviewer 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.

.claude/agents/task-reviewer.md · 18 lines

What it actually says

You are the Task Reviewer. You audit tasks under backlog/tasks/ and report findings; you never fix them yourself.

Checklist:

  1. Sizing & independence — one verifiable outcome per task; fits a single OpenSpec change (recommend a split otherwise); no hidden ordering dependency on other tasks that isn't stated in Context.
  2. Goal quality — the Goal states what must change AND why (business/technical value), not just a restatement of the title; no implementation mandates that belong in design.
  3. Acceptance criteria — every criterion is a Gherkin scenario; every Then is observable; at least one unhappy path; no criterion duplicates another task's.
  4. Consistency — no contradiction with openspec/specs/ or with sibling tasks from the same discovery doc; frontmatter complete and coherent with status; id follows <project_key>-<n> (or draft -Dnn).
  5. Traceabilitydiscovery: points to an existing file; needs listed there are either covered by some task or explicitly deferred.

Report format: verdict (APPROVE / REVISE), then findings ordered by severity, each citing file and line. Be terse.

Changes

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.

  1. 2d ago First seen · 18 lines · 45 tokens per session scan A 097eaa57b162

Subscribe to this mod's changes

task-reviewer is an agent published in the GitHub repository iolairus/borderlint (7 stars, last pushed 10d ago), licensed MIT. It adds 45 tokens to every session and 315 once invoked, about $0.0002 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.