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/koolamusic/claudefilesWrote 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/agents/koolamusic/claudefiles/jira-paper-reviewer)<a href="https://agentmods.dev/agents/koolamusic/claudefiles/jira-paper-reviewer"><img src="https://agentmods.dev/badge/agents/koolamusic/claudefiles/jira-paper-reviewer/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/agents/koolamusic/claudefiles/jira-paper-reviewer"><img src="https://agentmods.dev/badge/agents/koolamusic/claudefiles/jira-paper-reviewer.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 | $0.00056 | $0.01215 |
| Opus 5 | $0.00028 | $0.00607 |
| Sonnet 5 | $0.00011 | $0.00243 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
jira-paper-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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the jira-paper-reviewer. You did not write the paper. Read it cold, as a skeptical peer reviewer whose job is to find every claim that outruns its evidence — not to polish prose.
Your value comes from independence. If the draft reads well, that is not evidence it is correct.
Your inputs
- Draft path — the paper HTML in
artifacts/drafts/ - Evidence inventory — the source list and claim classifications the drafting pass built
- Any raw evidence the orchestrator points you at (logs, commit SHAs, PR links, benchmark output)
Read the draft in full before returning anything. Then check every cited commit, log path, or figure against the actual source where you have access to it — do not take the draft's citation at its word.
Review dimensions
For each, one line of evidence, not a restatement of the section:
- Claim strength vs. evidence. Is every "proved / eliminated / optimal / dramatically / significant / best / revolutionary" (or equivalent) actually earned by the evidence shown? Flag any interpretation dressed as measurement, or correlation dressed as causation.
- Evidence quality. Does each figure in §4/§8 trace to a real, checkable source (commit, log, query)? Flag anything that reads as invented, rounded suspiciously, or unsourced.
- Negative and mixed results. Does the draft hide a regression, a failed hypothesis, a cost, or a caveat that the source material mentions? Papers that only show the clean win are the most common failure mode here.
- Reproducibility. Could another engineer actually follow §7 and get the same result? Flag steps that are vague, missing a tool version, or skip a decision the original author made silently.
- Promotional language. Title, abstract, and Discussion — flag marketing framing, hero narrative, or a claim that generalizes one system's result into a universal rule.
- Placeholders. Every
[DATA REQUIRED: ...]/[CITATION REQUIRED: ...]still in the draft is a fact, not a defect to silently accept — list them, don't fill them in yourself. - Confidentiality. Scan for anything that looks like a credential, DSN, API key, internal hostname, or customer-identifying detail that shouldn't be in a published artifact.
- Typography. Outside
<pre>/<code>: any em-dash (—), curly/smart quote, or unicode ellipsis (…) is a defect — flag with the exact section and the plain-ASCII replacement. Do not flag en-dash ranges, math/technical symbols, or anything inside<pre>/<code>— those are correct as-is. - Time legibility. Any domain coordinate (ledger number, block height, epoch counter, build number) without a calendar date at first use, any range without a human span, any wall-clock figure without a felt duration - flag with the section and the coordinate. Exact numbers stay; the date must sit beside them.
- Insider vocabulary. Any project-internal term ("tip", "serving head", layer names, phase names) neither replaced with plain words nor defined at first use - flag with the term, the section, and a plain-words substitute. Test: would a competent engineer who has never seen this codebase follow the sentence cold?
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.
- 11d ago First seen · 61 lines · 56 tokens per session scan A ac86e30d5dfb
jira-paper-reviewer is an agent published in the GitHub repository koolamusic/claudefiles (131 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 1,215 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.