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.
npx agentmods add skills/tashian/tsm/credential-usagenpx skills add tashian/tsm --skill credential-usagegit clone --depth 1 https://github.com/tashian/tsmWrote 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.
[](https://agentmods.dev/skills/tashian/tsm/credential-usage)<a href="https://agentmods.dev/skills/tashian/tsm/credential-usage"><img src="https://agentmods.dev/badge/skills/tashian/tsm/credential-usage.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00037 | $0.01713 |
| Opus 5 | $0.00018 | $0.00856 |
| Sonnet 5 | $0.00007 | $0.00343 |
| Haiku 4.5 | $0.00004 | $0.00171 |
Grade A, and why
credential-usage 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "Authorization: Bearer $(tsm get gh-pat)" https://api.github.com/user How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using credentials from the tsm vault
When a task needs an API key, token, password, database URL, or other credential, use the local tsm vault before asking the user for it. The vault is biometric-gated (Touch ID) and the user has already approved the patterns below by installing this plugin.
1. Discover first
Run tsm list --json before assuming a credential is missing. Look for a name, description, or tag that matches what you need.
tsm list --json
# [{"name":"gh-pat","display_name":"GitHub PAT","description":"...","confirm":false,"tags":["github","git"]}, ...]
If tsm list shows the credential, use it via one of the patterns below. Only ask the user if no matching secret exists.
2. Pattern by tool category
Pick the pattern that matches the consuming tool. Never fall back to a less safe pattern just because it is shorter.
MCP server credentials
MCP server configs in .mcp.json accept command/args. Wrap the server in tsm run:
{
"github": {
"command": "tsm",
"args": ["run", "--env", "GITHUB_TOKEN=gh-pat", "--", "github-mcp-server"]
}
}
Env-var CLI tools (gh, openai, anthropic, aws, etc.)
For one-off invocations:
tsm run --env GITHUB_TOKEN=gh-pat -- gh pr list
tsm run --env OPENAI_API_KEY=openai-key -- openai api models.list
For one-shot value capture inside a single shell pipeline (no env-var leakage):
curl -H "Authorization: Bearer $(tsm get gh-pat)" https://api.github.com/user
File-flag tools (curl --cacert, psql --pgpass, gcloud --key-file)
Process substitution keeps the secret off disk entirely:
curl --cacert <(tsm get ca-cert) https://internal.example.com
PGPASSFILE=<(tsm get pg-prod --format pgpass) psql --no-password "service=mydb"
If the tool re-reads the file after first read, write to /dev/shm (memory-backed on Linux, ramdisk on macOS):
KEYFILE=$(mktemp /dev/shm/key.XXXXXX) && \
tsm get client-key --to-file "$KEYFILE" && \
some-tool --key "$KEYFILE" ; rm -f "$KEYFILE"
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.
- 4d ago First seen · 126 lines · 37 tokens per session scan A fa65d103b763
credential-usage is a skill published in the GitHub repository tashian/tsm (9 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,713 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
mks
MKS (Metasploit-Kali Server) tool preference guide. Mount in Phase 0/1 alongside the primary skill. Provides URL resolution, REST endpoint patterns, response parsing, error handling, and fallback rules for all MKS-backed Kali tools.
pentest
Penetration testing orchestrator that coordinates specialized attack agents. Provides attack indexes, methodology frameworks, and documentation. Execution delegated to specialized agents (SQL Injection, XSS, SSRF, etc.). Use for engagement planning and attack coordination.
authenticating
Authentication testing skill - automates signup, login, 2FA bypass, CAPTCHA solving, and bot detection evasion using Playwright MCP. Tests authentication security controls. Includes behavioral biometrics simulation, OTP handling, and automated account creation for security assessments.
common-appsec-patterns
Application security testing coordinator for common vulnerability patterns including XSS, injection flaws, and client-side security issues. Orchestrates specialized testing agents to identify and validate common application security weaknesses.
web-application-mapping
Comprehensive web application reconnaissance and mapping coordinator that orchestrates passive browsing, active endpoint discovery, attack surface analysis, and headless browser automation for complete application coverage.
cve-testing
CVE vulnerability testing coordinator that identifies technology stacks, researches known vulnerabilities, and tests applications for exploitable CVEs using public exploits and proof-of-concept code.