project-access

project-access is a skill for Claude Code, Codex from BlackBeltTechnology/pi-agent-dashboard. It costs 89 tokens per session (2,585 once invoked), scanned A, original, MIT.

A tool for reporting which folders a project can reach and proposing additional folder access in a project configuration file. A dashboard operator must approve each proposed access request.

In plain words
What is it for?
Use it to inspect project access, draft `.pi/access.json`, or submit folder-access proposals for operator approval.
Why use it?
It makes access needs explicit and prevents an agent from granting itself permission or silently changing access settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is "folders": [{ "path": "../shared-lib", "why": "sibling package used by tests" }],.

Good fit Use it to inspect project access, draft .pi/access.json, or submit folder-access proposals for operator approval.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard
agentmods
npx agentmods add skills/blackbelttechnology/pi-agent-dashboard/project-access

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 project-access

README.md
[![agentmods](https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/project-access/github.svg)](https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/project-access)
Your own site
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/project-access"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/project-access/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 project-access

Your own site · 80×15
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/project-access"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/project-access.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,585 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 $0.00089 $0.02585
Opus 5.5 $0.00036 $0.01034
Sonnet 5.5 $0.00018 $0.00517
Haiku 4.5 $0.00009 $0.00259

Measured today against content hash 5c77feb3ac08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-access 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 today.

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.

curl -s "$BASE/api/health"
packages/extension/.pi/skills/project-access/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Access

Work out which folders outside a project its agents need, and ask the dashboard operator to approve them once, ahead of time, instead of one prompt per denial.

You only ever propose. The operator answers per line in the dashboard. Nothing in this skill grants access, changes configuration, or answers for the operator.

Setup — server URL

Discover the server the way the pi-dashboard skill does (config port, default 8000):

PORT=$(grep -m1 '"port"' ~/.pi/dashboard/config.json 2>/dev/null | grep -o '[0-9]*'); PORT=${PORT:-8000}
BASE="http://localhost:$PORT"
curl -s "$BASE/api/health"

(grep -m1 takes the top-level port; the config also nests other port keys.)

If health does not answer, say the dashboard is not running and stop (every mode needs it, except reading .pi/access.json). When auth is enabled, pass the JWT cookie as the pi-dashboard skill describes (curl -b "pi_dash_token=…").

Project root = git rev-parse --show-toplevel from the cwd; when that fails, the cwd if it holds a .pi directory. A root with neither .git nor .pi is not a project: say so and stop.

Profile — .pi/access.json (format v1)

Optional file in the project root. A proposal only: the dashboard server never reads it, and the file alone grants nothing. Its contents take effect only through an approved provision request.

{
  "version": 1,
  "folders": [{ "path": "../shared-lib", "why": "sibling package used by tests" }],
  "remote": ["lan"]
}
  • folders[].path: absolute, ~/-rooted or relative to the project root. why is optional, plain text, shown to the operator (cut at 200 characters).
  • remote (optional): any of lan, internet, device. A goal only points the operator at the Remote access dialog; nothing is configured for them.
  • At most 32 folder lines.
  • An unknown version (or a missing/non-numeric one): refuse. Say the file is not version 1, show the value found, and do not read or send any of it.

Read the full file on GitHub · 191 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today First seen · 191 lines · 89 tokens per session scan A 5c77feb3ac08

Subscribe to this mod's changes

project-access is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (329 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,585 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-22.

Related

Other skills, from other repositories