secrets-handling

A set of procedures for keeping passwords, API keys, tokens, private keys, personal data, and other sensitive text from being exposed.

In plain words
What is it for?
Use it when reading configuration or logs, debugging integrations, handling clipboard or screenshot content, writing documentation, or sending messages.
Why use it?
It reduces the risk of secrets appearing in prompts, files, logs, screenshots, shell commands, or messages. It also helps identify and redact sensitive values before they are shared.

Skill for Claude CodeCodex

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 skills/codeinfinity1/stram/secrets-handling
Any agent
npx skills add CodeInfinity1/Stram --skill secrets-handling
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 420 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 $0.00032 $0.00420
Opus 5 $0.00016 $0.00210
Sonnet 5 $0.00006 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured yesterday against content hash 34e738dacd80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

secrets-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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/redact_text.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agent-core/secrets-handling/SKILL.md · 72 lines

What it actually says

Secrets Handling

Purpose

Protect secrets in prompts, logs, files, screenshots, clipboard, shell commands, provider configs, and external messages.

When To Use

Use when reading env/config/logs, debugging providers, handling clipboard/screenshots, writing docs, sending messages, or integrating APIs.

Inputs And Evidence

  • Secret-bearing source, redaction requirements, destination, and tool risk.
  • Provider status or config output.

Tool Map

  • system_status
  • voice_provider_status
  • read_file
  • os_clipboard_read
  • screen_captures
  • message-approval-policy
  • agent_skill_script_catalog
  • agent_skill_script_run

Native Scripts

  • scripts/redact_text.py: mechanically redacts likely tokens, private keys, and credential assignments from supplied text. This is a redaction helper, not semantic intent routing.

Workflow

  1. Identify likely secret-bearing sources.
  2. Minimize reading and copying.
  3. Redact values in responses and notes.
  4. Store secrets only in approved env/secret providers.
  5. Prevent external-visible sends with secrets.
  6. Report presence/missing rather than raw values.

Native Implementation Boundaries

  • Use Stram redaction/status/policy tools.
  • Do not import external secret scanners as implementation unless wrapped natively.
  • Add scanners as Stram-owned tools if needed.

Safety And Approval

  • Never print full tokens or private keys.
  • Treat clipboard and screenshots as sensitive.
  • Do not commit secrets.

Verification

  • Check outputs are redacted.
  • Confirm secret setup by presence flags, not values.
  • Run dependency/security checks when relevant.

Failure Modes

  • Echoing .env values.
  • Sending logs with tokens to channels.
  • Saving secrets in notes.

References

  • Shortlist item: secrets-handling.
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. yesterday First seen · 72 lines · 32 tokens per session scan A 34e738dacd80

Subscribe to this mod's changes

secrets-handling is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 32 tokens to every session and 420 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.