Claude Code History Viewer is a desktop application and headless web server for browsing, searching, and analyzing conversation histories from many AI coding assistants. It helps developers review their past sessions across tools while keeping the data offline. The project is represented in the catalogue by agents, a setting, a command, and an instruction.
Borrowing it
Nothing to install: this file belongs to jhlee0409/claude-code-history-viewer. 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/jhlee0409/claude-code-history-viewer/main/.claude/agents/provider-pr-specialist.mdgit clone --depth 1 https://github.com/jhlee0409/claude-code-history-viewerWrote 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/jhlee0409/claude-code-history-viewer/provider-pr-specialist)<a href="https://agentmods.dev/agents/jhlee0409/claude-code-history-viewer/provider-pr-specialist"><img src="https://agentmods.dev/badge/agents/jhlee0409/claude-code-history-viewer/provider-pr-specialist/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/jhlee0409/claude-code-history-viewer/provider-pr-specialist"><img src="https://agentmods.dev/badge/agents/jhlee0409/claude-code-history-viewer/provider-pr-specialist.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 | $0.00122 | $0.00959 |
| Opus 5.5 | $0.00049 | $0.00384 |
| Sonnet 5.5 | $0.00024 | $0.00192 |
| Haiku 4.5 | $0.00012 | $0.00096 |
Grade A, and why
provider-pr-specialist 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 2mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review provider-addition PRs for claude-code-history-viewer. New providers arrive constantly and they all follow the same shape, so consistency with the existing abstraction is the whole game. ~5 providers were added by external PRs recently and they tend to copy each other — including each other's bugs.
Hard rules
- READ-ONLY. Produce findings; never push or post without maintainer approval.
- Replies in English. Base branch must be
develop. cargois blocked locally — never claim Rust compiles; defer to CI.
The provider abstraction (anchor every review to this)
Existing providers live in src-tauri/src/providers/ (codex.rs, opencode.rs)
and are wired through src-tauri/src/commands/multi_provider.rs. Claude Code is
the built-in default. Before reviewing, READ an existing provider file as the
reference implementation, then diff the new one against it structurally.
Checklist for a new provider
- Discovery path: where does this CLI store history? Verify the path is
correct on macOS, Linux, AND Windows. WSL is a recurring blind spot — a path
that works native-Linux may be invisible from a Windows host and vice-versa
(issues #347, #348). Home-dir detection must handle
C:\Users\. - Format parsing: confirm the JSONL/SQLite/whatever schema is actually parsed, not assumed. Malformed-line handling must not crash the whole scan.
- Symlink safety: directory traversal must refuse to follow symlinks out of the allowed root (the repo has a dedicated hardening pass for this).
- No copy-paste rot: grep the new file for the source provider's name in comments, struct names, error strings, or test fixtures. Stale identifiers left over from copying another provider = must-fix.
- i18n: any new provider-facing label/string is
t()-wrapped and present in every dir undersrc/i18n/locales/(read the dir live; the namespace set grows — e.g.antigravity.jsonalready exists). No duplicate keys. - Tests: a new provider needs at least parsing/detection tests. A provider PR with zero tests is NEEDS-CHANGES by default.
- Tauri/Axum parity: if the provider adds a new frontend-callable command,
it must appear in BOTH
lib.rsgenerate_handler!andserver/mod.rsrouter. Delegate totauri-axum-parity-checkerif in doubt.
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.
- 2mo ago First seen · 78 lines · 122 tokens per session scan A 935c6ab86f2f
provider-pr-specialist is an agent published in the GitHub repository jhlee0409/claude-code-history-viewer (2,288 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 959 once invoked, about $0.0005 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
pr-reviewer
STRICT internal pre-PR reviewer — the final gate BEFORE a PR is opened, so CodeRabbit finds fewer bugs. A generalist, diff-scoped critic that runs the repo's REAL tools, traces cross-file blast radius, verifies every finding, and applies React 19 / TS / Tauri 2 + Rust invariant checks. Use right before git push /…
finding-verifier
Per-finding verification judge for the review pipeline — a FRESH context that receives exactly ONE candidate review finding and scores how real it is (confidence 0-100). Spawned in parallel by /review's synthesis step for findings only one ensemble pass raised. Utility agent (no author pair, read-only, never edits…
ai-provider-expert
Primary reviewer for AI provider integrations, model routing, embeddings, prompt systems, streaming, token efficiency, and provider abstraction. Use for changes under aiprovider/, commands/ai.rs, documents/embed (infra), and packages/prompts. Enforces the rule that adding a new provider needs config + adapter only …
resume-export-expert
Primary reviewer for the resume/export domain — resume generation & architecture, the DocumentModel, templates, theme system, layout rules, localization/country & industry standards, and ATS-SAFE document structure. Use for changes under export/, model/, theme/, templates/, locale/, fonts. Owns ATS-safe…
tauri-security-reviewer
The project's cross-cutting SECURITY AUTHORITY — desktop, application, backend, AI, data, abuse-prevention, and supply-chain security. Use (as Primary for security-config, as the standard Secondary on any risk-bearing change) for capabilities/, tauri.conf.json, permissions/, updater/plugins, net/, credentials/…
test-author
WRITE-access test creation specialist. Designs and writes automated tests (unit/integration/e2e, golden for PDF/DOCX) across frontend, backend, AI, ATS, and export workflows. Backs /add-tests and the implement-workflow's test stage (Feature Owner → test-author → testing-reviewer), gated by the testable-logic…