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/the-17/agentsecrets/openclawnpx skills add The-17/agentsecrets --skill openclawgit clone --depth 1 https://github.com/The-17/agentsecretsWhat 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 | $0.00021 | $0.01454 |
| Opus 5 | $0.00010 | $0.00727 |
| Sonnet 5 | $0.00004 | $0.00291 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade A, and why
agentsecrets 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 3d 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.
Instead of using `curl`, always use the `call` proxy. The proxy injects the secret securely: How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentSecrets — Zero-Knowledge Secrets Infrastructure
You manage the full credentials lifecycle autonomously using the agentsecrets CLI or Model Context Protocol (MCP) server.
You are the operator. You never see the actual credential values.
Security & Privacy Rules (with Native Mitigations)
[!WARNING] Outbound Data Exfiltration Risk & Allowlist Mitigation: Although you can autonomously trigger API calls through the proxy, AgentSecrets strictly mitigates exfiltration risks via the Workspace Domain Allowlist. Outbound requests are blocked by default unless the destination domain is explicitly authorized. Only workspace administrators can alter the allowlist (which requires local password verification).
Rogue credential modification & Password Mitigation: Unsupervised scripts or agents are prevented from tampering with critical environments. Creating, modifying, or deleting secrets in the
productionenvironment (or globally across all environments) requires Local Password Verification.Plaintext Exposure & Zero-Knowledge Enforcement: You must never attempt to retrieve or display plaintext credential values. The
agentsecrets secrets getcommand is strictly restricted for agents. OS Keychain storage is further isolated by thekeychain-authdaemon's Process Hash Verification to prevent process hijacking.Outbound Request Auditing: All outbound requests and enforcement outcomes are automatically recorded in the local SQLite database (
~/.agentsecrets/audit.db). The forensic log is cryptographically chain-hashed (chain_hash = sha256(prev_id + current_id + created_at)) to guarantee log immutability and non-repudiation.
Core Workflow Commands
Always start by verifying context:
agentsecrets status # Shows workspace, project, environment
agentsecrets secrets list # Lists available keys
If not initialized or logged out, tell the user to run agentsecrets login. For new projects, run agentsecrets init --storage-mode 1.
What ships with it
3 files 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.
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.
- 3d ago First seen · 127 lines · 21 tokens per session scan A 33361ace4fbe
agentsecrets is a skill published in the GitHub repository The-17/agentsecrets (172 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 1,454 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
1password
Manage secrets via 1Password CLI (op). Read, create, and inject secrets. Provides whitelisted access for other skills (ask-curl, GitHub, etc.) via op:// secret references and 1Password Environments.
canary
Scans your OpenClaw environment for leaked secrets — API keys, tokens, credentials in .env files, installed skills, and shell history. Runs silently on startup, deep scans on demand. Fixes issues with your permission.
secrets-gitleaks
Hardcoded secret detection and prevention in git repositories and codebases using Gitleaks. Identifies passwords, API keys, tokens, and credentials through regex-based pattern matching and entropy analysis. Use when: (1) Scanning repositories for exposed secrets and credentials, (2) Implementing pre-commit hooks to…
secrets-gitleaks
Hardcoded secret detection and prevention in git repositories and codebases using Gitleaks. Identifies passwords, API keys, tokens, and credentials through regex-based pattern matching and entropy analysis. Use when: (1) Scanning repositories for exposed secrets and credentials, (2) Implementing pre-commit hooks to…
security-hardening
Security audit and hardening for AI agents — credential hygiene, secret scanning, prompt injection defense, data leakage prevention, and privacy zones.
server-setup
Initialize tRPC with initTRPC.create(), define routers with t.router(), create procedures with .query()/.mutation()/.subscription(), configure context with createContext(), export AppRouter type, merge routers with t.mergeRouters(), lazy-load routers with lazy().