What is credential-handling?

A policy for using credentials and test accounts on a project's own surfaces, including logging in and testing authenticated features.

Use it when a task requires account creation, authentication, SSH access, or testing behind a login.

It explains when agents may use credentials supplied by the founder and separates testing access from financial actions or public launches.

credential-handling — Skill for Claude Code by nikolamin

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.

Any agent

npx skills add nikolamin/claude-coordinator-kit --skill credential-handling

Clone the repo

git clone --depth 1 https://github.com/nikolamin/claude-coordinator-kit

Made for: Claude Code.

Or install coordinator-kit, the plugin that ships this one along with the rest of its 15 skills, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/credential-handling/github.svg)](https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/credential-handling)

Your own site

<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/credential-handling"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/credential-handling/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/credential-handling"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/credential-handling.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 484 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.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.00484
Opus 5.5	$0.00019	$0.00194
Sonnet 5.5	$0.00009	$0.00097
Haiku 4.5	$0.00005	$0.00048

Measured 1mo ago against content hash bf0bac8be67e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

credential-handling 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.

plugins/coordinator-kit/skills/credential-handling/SKILL.md · 36 lines

What it actually says

Credential and account handling

Use the project's existing account-access grants to complete the authorized task, including test-account creation and authenticated testing when covered. Do not re-ask for the same grant. The plugin itself grants no access. A pasted credential authorizes its stated task use; it does not widen scope to financial transactions, production changes, public releases or unrelated sends.

If a platform limit or device-bound 2FA blocks one step, state the real reason and complete everything else. Hand back only that specific user-only step; do not abandon the entire task because it involves credentials. Required verification remains pending until actually completed.

Never print a credential file's contents: no cat/head/tail/echo on .env or equivalent, local or remote. Inspect names only; load values without exposing them in output.
Do not put expanded secrets in command arguments: shell errors/process listings can expose them even if nothing explicitly echoes. Use supported config, environment, stdin or secret stores, and check diagnostic output is redacted.
No credentials in state, the coordination database, memory, logs, reports, commits, generated fixtures, backup patches or derived scratch copies. This includes discovered/decoded secrets, not only ones pasted by the founder. If persistence is needed, use the approved secret store or gitignored local config. Record locations, not values.
Enforce read-only production database access structurally with a restricted role or supported session/transaction control. Validate the mechanism in a safe fixture/test environment and confirm it is active on the real connection. Do not try a potentially successful production write merely to demonstrate denial; read-only task authorization does not permit that probe.
Local restores still contain restricted data and may retain live delivery destinations. Keep identifiers-only evidence where required and isolate outbound integrations before running.

Restate these operative rules in any agent brief involving credentials/auth/DB access. Naming a skill alone does not guarantee another agent loaded it. Existing founder decisions about known issues remain in the canonical record; check them before repeating an unchanged escalation.

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.

1mo ago Changed · -31 lines · -217 tokens per session bf0bac8be67e
2mo ago First seen · 67 lines · 264 tokens per session scan A f64aae4937cd

Subscribe to this mod's changes

credential-handling is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 29d ago), licensed MIT. It adds 47 tokens to every session and 484 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 2026-08-31.