project-confirm

project-confirm is a command for coding agents from krishnesh7/claude-usage-analytics. It costs 31 tokens per session (316 once invoked), scanned A, original, MIT.

A command for showing which registered project the current coding session belongs to and resolving that assignment again. A project here means the codebase or workspace associated with the session.

In plain words
What is it for?
Use it to inspect project resolution, list registered projects, retag a session to an existing project, or register and tag a new project when no match exists.
Why use it?
It helps detect when a session was tagged to the wrong project or when several projects could match the current folder. It then provides the information needed to correct the tag.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-usage-analytics plugin — 2 skills, 10 commands shipped together

Install

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.

agentmods
npx agentmods add commands/krishnesh7/claude-usage-analytics/project-confirm
Clone the repo
git clone --depth 1 https://github.com/krishnesh7/claude-usage-analytics

Or install claude-usage-analytics, the plugin that ships this one along with the rest of its 2 skills, 10 commands.

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-confirm

README.md
[![agentmods](https://agentmods.dev/badge/commands/krishnesh7/claude-usage-analytics/project-confirm.svg)](https://agentmods.dev/commands/krishnesh7/claude-usage-analytics/project-confirm)
Your own site
<a href="https://agentmods.dev/commands/krishnesh7/claude-usage-analytics/project-confirm"><img src="https://agentmods.dev/badge/commands/krishnesh7/claude-usage-analytics/project-confirm.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00316
Opus 5 $0.00015 $0.00158
Sonnet 5 $0.00006 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured 4d ago against content hash 6dfcde99505f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-confirm 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 4d 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.

commands/project-confirm.md · 27 lines

What it actually says

Show the current session's project assignment and confidence, then offer to correct it if needed.

Run the following and present the results clearly:

CU=${CLAUDE_PLUGIN_ROOT}/bin/cu

# Resolve the current directory
echo "=== Project resolution for: $(pwd) ===" && \
$CU session-resolve --cwd "$(pwd)"

After showing the output, explain:

  • EXACT/SUBDIR/WORKTREE — correctly auto-tagged, no action needed
  • FUZZY — loosely matched; ask: "Is this correct? If not, which registered project should it be?" Then run: $CU project tag --session $CLAUDE_SESSION_ID --name <correct-name>
  • AMBIGUOUS — multiple matches; ask: "Which of these projects does this session belong to?" Then run: $CU project tag --session $CLAUDE_SESSION_ID --name <chosen-name>
  • UNMATCHED — ask: "What project is this session for?" Options:
    1. Tag an existing project: $CU project tag --session $CLAUDE_SESSION_ID --name <name>
    2. Register & tag a new one: run cu project init <name> in the terminal, then tag

Also show registered projects with: $CU project list

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. 4d ago First seen · 27 lines · 31 tokens per session scan A 6dfcde99505f

Subscribe to this mod's changes

project-confirm is a command published in the GitHub repository krishnesh7/claude-usage-analytics (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 316 once invoked, about $0.0002 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 2026-08-31.