agentmods.dev

credential-usage

credential-usage is a skill for Claude Code from tashian/tsm. It costs 106 tokens per session (2,412 once invoked), scanned B, original, MIT.

A safe procedure for tasks that need an API key, password, token, or other secret, using a local credential vault first.

In plain words
What is it for?
It helps discover matching credentials and use them with supported servers or command-line tools through safer environment-variable patterns.
Why use it?
It avoids putting secrets directly into requests or asking for them unnecessarily when a stored credential may already exist.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the tsm plugin — 1 skill shipped together

not rated 10repo changed 1mo ago B scan 106 tokens original MIT

Good fit It helps discover matching credentials and use them with supported servers or command-line tools through safer environment-variable patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tashian/tsm/credential-usage
View source ↗ tashian/tsm
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 tashian/tsm --skill credential-usage
Clone the repo
git clone --depth 1 https://github.com/tashian/tsm

Made for: Claude Code.

Or install tsm, the plugin that ships this one along with the rest of its 1 skill.

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 credential-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/tashian/tsm/credential-usage/github.svg)](https://agentmods.dev/skills/tashian/tsm/credential-usage)
Your own site
<a href="https://agentmods.dev/skills/tashian/tsm/credential-usage"><img src="https://agentmods.dev/badge/skills/tashian/tsm/credential-usage/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 credential-usage

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashian/tsm/credential-usage"><img src="https://agentmods.dev/badge/skills/tashian/tsm/credential-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,412 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00106 $0.02412
Opus 5.5 $0.00042 $0.00965
Sonnet 5.5 $0.00021 $0.00482
Haiku 4.5 $0.00011 $0.00241

Measured 1mo ago against content hash 8089ab84b01a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

credential-usage scanned grade B with 2 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

Not "Your vault has one GitHub entry, `gh-token` (classic PAT with repo + read:org), so I used that. The token never appears in `.mcp.json` or any argv. The first start will pop a Touch ID prompt; later starts won't." bu

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Use whenever a task needs an API key, token, password, database URL, certificate, or any other credential. That includes configuring an MCP server, calling an authenticated API with curl, running gh/aws/open
plugin/skills/credential-usage/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using credentials from the tsm vault

tsm is a Touch ID-gated secrets vault on this Mac. The user installed this plugin so you pull credentials from it instead of asking for them. tsm list, tsm get, and tsm status are allowlisted for you. tsm run is not, because it runs whatever command follows --, so the user approves each one; every other subcommand (add, edit, remove, reset, init, config set) changes the vault and is the user's to run. The first vault access in a session blocks on a system Touch ID dialog until the user responds. Do not kill or retry it. The dialog shows the command that receives the secret, so keep that command short and readable: the user approves what the dialog shows.

Workflow

  1. Look before asking. tsm list <term>... --json lists the entries where any term appears in the name, display name, description, or a tag, ignoring case. Pass the service and its synonyms (tsm list aws amazon --json) rather than filtering the full list yourself. The output is one JSON array with one entry per line, each {"name", "display_name", "description", "confirm", "tags"}, never values. One match: use it. Several plausible: ask which. None ([]): say so, propose a kebab-case name, and stop. Do not ask for a value while a match exists. If a command fails, stdout is empty, the exit code is 1, and with --json stderr holds {"error": {"code", "name", "message"}}; name is auth_required, auth_unavailable, vault_locked, or secret_not_found.
  2. Pick the carrier for the tool (below). Prefer tsm run whenever the tool reads an environment variable.
  3. Do the task, then report the task, not the credential handling (see "What to tell the user").

The one rule: the value never lands in an argument list

Anything in a process's argv is visible in ps to every user on the machine and lands in shell history. So the value travels by environment variable, file descriptor, or 0600 temp file, never as part of a command line. $(tsm get x) inside a flag value breaks the rule even though it looks tidy, and eval "$(tsm get x --format 'env X')" plants it in the parent shell for its whole lifetime.

Read the full file on GitHub · 100 lines

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 Changed 8089ab84b01a
  2. 1mo ago Changed 3af507f27a1d
  3. 1mo ago Changed · +2 lines 981ea2c27690
  4. 1mo ago Changed · -51 lines · -3 tokens per session scan A → B 00c40de5d427
  5. 1mo ago Changed · +23 lines · +72 tokens per session 1271a6fb634e
  6. 2mo ago First seen · 126 lines · 37 tokens per session scan A fa65d103b763

Subscribe to this mod's changes

credential-usage is a skill published in the GitHub repository tashian/tsm (10 stars, last pushed 11d ago), licensed MIT. It adds 106 tokens to every session and 2,412 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Securityclaudeclaude-code-plugincodexcybersecurity
Related

credential-usage compared with skills from other repositories

credential-usage next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
credential-usagetashian/tsmSkill1011d agoMITB106Claude Code
mksStickman230/claude-pentestSkill1335mo agoMITA54Claude Code
pentestStickman230/claude-pentestSkill1335mo agoMITA50Claude Code
authenticatingStickman230/claude-pentestSkill1335mo agoMITA54Claude Code
common-appsec-patternsStickman230/claude-pentestSkill1335mo agoMITA42Claude Code
web-application-mappingStickman230/claude-pentestSkill1335mo agoMITA38Claude Code
cve-testingStickman230/claude-pentestSkill1335mo agoMITA36Claude Code