jira-verifier

jira-verifier is an agent for Claude Code from koolamusic/claudefiles. It costs 61 tokens per session (1,924 once invoked), scanned A, original, MIT.

A post-execution agent that checks whether the current codebase actually delivers a sprint's goal. It reviews the finished result itself, rather than only trusting execution notes or inspecting the change list.

In plain words
What is it for?
Use it after a sprint to compare the goal, plans, acceptance criteria, context, and reported execution with what the repository now does.
Why use it?
It can expose work that was marked complete but does not satisfy the intended behavior or locked project decisions.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the jira plugin — 13 commands, 9 agents shipped together

Good fit Use it after a sprint to compare the goal, plans, acceptance criteria…

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add koolamusic/claudefiles
Claude Code
/plugin install jira

Made for: Claude Code.

Or install jira, the plugin that ships this one along with the rest of its 13 commands, 9 agents.

Wrote 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.

agentmods badge for jira-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/koolamusic/claudefiles/jira-verifier.svg)](https://agentmods.dev/agents/koolamusic/claudefiles/jira-verifier)
Your own site
<a href="https://agentmods.dev/agents/koolamusic/claudefiles/jira-verifier"><img src="https://agentmods.dev/badge/agents/koolamusic/claudefiles/jira-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00061 $0.01924
Opus 5 $0.00030 $0.00962
Sonnet 5 $0.00012 $0.00385
Haiku 4.5 $0.00006 $0.00192

Measured 7d ago against content hash cc735f044fe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

jira-verifier scanned grade A with 1 finding 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Where possible, run a shell command to confirm behavior (`bash -c '...'`, a curl against a local server if one is documented in README, a CLI invocation). Run only safe, read-only or self-contained commands. Never modi
plugins/jira/agents/jira-verifier.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the jira-verifier. Your one job: read the sprint goal, walk the codebase as it exists right now, and report whether the goal has actually been delivered.

You are NOT checking the diff (that's jira-reviewer). You are NOT checking test coverage (that's jira-nyquist). You ARE asking: "if a fresh person opened this repo today, would they observe the goal as fulfilled?"

Your inputs

The orchestrator (/jira:execute) provides:

  1. Sprint slug
  2. Sprint dir.jira/sprints/<slug>/
  3. All plan paths.jira/sprints/<slug>/*-PLAN.md (read every one — wave plans share a sprint goal but each plan covers a subset)
  4. CONTEXT path.jira/sprints/<slug>/CONTEXT.md (locked decisions; cross-check each was implemented)
  5. Feature paths.jira/sprints/<slug>/features/*.feature (acceptance predicates; cross-check claimed and sensed)
  6. EXECUTION path.jira/sprints/<slug>/EXECUTION.md (what the executor reports it did; treat as a claim, not evidence)
  7. Verification output path.jira/sprints/<slug>/VERIFICATION.md (write your report here)
  8. Verification template${CLAUDE_PLUGIN_ROOT}/templates/sprint/VERIFICATION.md

Project context

Before verifying, scan for project-specific rules:

  • Read ./CLAUDE.md if present.
  • Check .claude/skills/ and ~/.claude/skills/ — if either exists, list subdirectories and read each SKILL.md (lightweight index). Apply skill rules during verification (e.g. a react-best-practices skill may define what "delivered" means for React code).

Evidence types

Every claim in VERIFICATION.md names exactly one of these types:

  • command — exact command, cwd, and observed output.
  • source-auditpath:line or the exact search query proving a static property.
  • browser — route, interaction performed, what was observed (screenshot path if captured).
  • artifact — a generated file, report, or document; cite its path.
  • external-source — URL, issue, or doc page used as authority.
  • N/A: <reason> — why an outcome or decision row does not apply.

Read the full file on GitHub · 129 lines

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. 7d ago First seen · 129 lines · 61 tokens per session scan A cc735f044fe9

Subscribe to this mod's changes

jira-verifier is an agent published in the GitHub repository koolamusic/claudefiles (131 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,924 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

onboard-guide

Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.

smicolon/ai-kit · 46 tokens

scrum-master

Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.

LuisFelipeMoro/Harness-devkit · 24 tokens

jira-analyst

Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…

ngocsangyem/MeowKit · 72 tokens

pm-advisor

You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".

VandanaAjayDubey111/great-pm · 123 tokens

goals-onboarding

Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…

41fred/ace-level1 · 206 tokens