agentmods.dev

pinkbee-mcp: Skill for Claude Code

.agents/skills/har-explorer/SKILL.md

har-explorer is a skill for Claude Code, Codex from LaurensdeGraaff/pinkbee-mcp. It costs 47 tokens per session (312 once invoked), scanned A, original, MIT.

A workflow for examining Chrome HAR files, which are saved records of browser network requests. It extracts API calls, payloads, responses, errors, and their order while hiding sensitive values.

In plain words
What is it for?
Use it to investigate API behavior from a HAR file or provide reliable endpoint and payload details for implementation work.
Why use it?
It makes captured browser traffic easier to understand without exposing cookies, passwords, tokens, or personal data. It helps identify how a web application communicates with its API.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is LaurensdeGraaff/pinkbee-mcp's own configuration. It tells Claude Code and Codex how to work on pinkbee-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pinkbee-mcp configures →

not rated 0repo 1mo ago A scan 47 tokens original MIT
View source ↗ LaurensdeGraaff/pinkbee-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to LaurensdeGraaff/pinkbee-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/LaurensdeGraaff/pinkbee-mcp/main/.agents/skills/har-explorer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LaurensdeGraaff/pinkbee-mcp

Made for: Claude Code, Codex.

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 har-explorer

README.md
[![agentmods](https://agentmods.dev/badge/skills/laurensdegraaff/pinkbee-mcp/har-explorer/github.svg)](https://agentmods.dev/skills/laurensdegraaff/pinkbee-mcp/har-explorer)
Your own site
<a href="https://agentmods.dev/skills/laurensdegraaff/pinkbee-mcp/har-explorer"><img src="https://agentmods.dev/badge/skills/laurensdegraaff/pinkbee-mcp/har-explorer/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.

agentmods 80×15 button for har-explorer

Your own site · 80×15
<a href="https://agentmods.dev/skills/laurensdegraaff/pinkbee-mcp/har-explorer"><img src="https://agentmods.dev/badge/skills/laurensdegraaff/pinkbee-mcp/har-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00047 $0.00312
Opus 5.5 $0.00019 $0.00125
Sonnet 5.5 $0.00009 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 1mo ago against content hash 2eb3a7c82eeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

har-explorer 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.

.agents/skills/har-explorer/SKILL.md · 30 lines

What it actually says

HAR Explorer

Inspect .har files as structured JSON. Focus on log.entries; use jq or a short Python script instead of loading a large HAR wholesale.

Workflow

  1. Confirm log.entries, entry count, and capture time range.
  2. Summarize request time, method, host, path, status, MIME type, duration, and initiator when available.
  3. Group repeated calls by method and normalized path. Separate API/XHR/fetch calls from static assets.
  4. Highlight redirects, failures, HTTP status >= 400, slow calls, and unusual order.
  5. Inspect headers, query parameters, request bodies, and responses only for relevant calls.
  6. Finish with concise call-flow notes and a table of important endpoints.
  7. For MCP implementation work, pass endpoint and payload findings to the mcp-development workflow; this skill does not itself modify application code.

Safety

  • Never print cookies, authorization headers, session IDs, CSRF tokens, API keys, passwords, or complete personal data.
  • Redact sensitive values while preserving field names and payload shapes.
  • Do not modify the HAR file.
  • State when response bodies are missing because Chrome did not save them.
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. 1mo ago First seen · 30 lines · 47 tokens per session scan A 2eb3a7c82eeb

Subscribe to this mod's changes

har-explorer is a skill published in the GitHub repository LaurensdeGraaff/pinkbee-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 312 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 2026-09-27.

DebuggingResearch
Related

har-explorer compared with skills from other repositories

har-explorer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
har-explorerLaurensdeGraaff/pinkbee-mcpSkill01mo agoMITA47Claude Code, Codex
systematic-debuggingopen-metadata/OpenMetadataSkill16ktodayApache-2.0A37Claude Code
log-error-digestzebbern/claude-code-guideSkill4.7kyesterdayMITA71Claude Code, Codex
cwv-optimizeradobe/skillsSkill325todayApache-2.0A112Claude Code
ci-fixersipyourdrink-ltd/bernsteinSkill1.2ktodayApache-2.0A15Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthogSkill41ktodaynoneA76Claude Code, Codex
triaging-web-analytics-supportPostHog/posthogSkill41ktodaynoneA151Claude Code, Codex