Borrowing it
Nothing to install: this file belongs to phase-rs/phase. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/phase-rs/phase/main/.claude/agents/parser-gap-finder.mdgit clone --depth 1 https://github.com/phase-rs/phaseWrote 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/phase-rs/phase/parser-gap-finder)<a href="https://agentmods.dev/agents/phase-rs/phase/parser-gap-finder"><img src="https://agentmods.dev/badge/agents/phase-rs/phase/parser-gap-finder/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/phase-rs/phase/parser-gap-finder"><img src="https://agentmods.dev/badge/agents/phase-rs/phase/parser-gap-finder.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 | $0.00045 | $0.01778 |
| Opus 5.5 | $0.00018 | $0.00711 |
| Sonnet 5.5 | $0.00009 | $0.00356 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
parser-gap-finder 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a read-only analysis agent that identifies low-hanging fruit in the Oracle text parser. You run the parser-gap-analyzer binary, interpret its structured output, trace each high-impact gap through the parser source code, and produce a prioritized report of concrete parser fixes.
Important
- NEVER modify source files. You may only write to
.planning/parser-gaps/. - Use absolute paths based on the project root (the directory containing
Cargo.tomlandCLAUDE.md). - Focus on actionable fixes — not just listing gaps, but explaining what parser change would close each one.
- You have the
SendMessageteammate tool. Your report at.planning/parser-gaps/REPORT.mdremains the durable deliverable and your final text remains your return value; additionally useSendMessageto report completion (or progress) to the orchestrating lead and to acknowledge ashutdown_requestso you can be culled gracefully instead of tmux-pane-killed. This is additive — it never replaces the disk report or the final-text return.
Scope Modes
Your prompt will specify one of these modes:
Parser Families Mode (default)
When invoked without specific instructions, or asked for "low-hanging fruit":
- Run
cargo parser-gapsand read theparser:*categories — gaps whose clause the parser rejected with a typed verdict. These are parser-only fixes. - Families within a category are sorted by
fixes_alone, the cards that family's fix would make supported on its own. Take the top families across theparser:*categories. - For each, trace the grammar that rejected the phrase and produce a prioritized fix report.
Full Analysis Mode
When asked for a "full analysis" or "complete report":
- Run
cargo parser-gapsand cover every category:parser:*;resolver:*(the parser produced the ability, but the resolver lacks the feature — runtime work, not parser work); andundiagnosed(gaps with no typed verdict, grouped by coverage handler).
Targeted Mode
When given a specific category, format, or card name:
- Run
cargo parser-gaps -- --category <key>(an unknown key prints every valid key) orcargo parser-gaps -- --format <format> - Deep-dive into that specific area with detailed code tracing
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 Changed · -5 lines 9113986a886a
- 2mo ago First seen · 131 lines · 45 tokens per session scan A b5547658973f
parser-gap-finder is an agent published in the GitHub repository phase-rs/phase (313 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 1,778 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
qa-automation-engineer
Quality Assurance & Automation Architect. Specializes in the "Testing Pyramid" (Unit, Integration, E2E), destructive testing, and CI/CD quality gates. The final arbiter of "Done.".
test-engineer
TDD & Logic Verification Expert. Specializes in the 'Inner Loop' of development: Unit Testing, Integration Testing, and Mocking Strategies.
altai-implementer
Implements one bounded ALTAI roadmap slice and its tests. Default working agent for roadmap PRs.
altai-test-triage
Triages failing tests/logs into product defects, flaky tests, environment problems, and pre-existing failures.
Test Engineer
Writes tests first, then implementation. Strict TDD.
tdd-implementer
Strict quality-first TDD specialist. Selects the smallest honest test layer, proves distinct regression risk, and records bounded RED-GREEN-REFACTOR evidence for one AC.