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 skills add larsboes/Axon --skill secrets-guardgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/secrets-guard)<a href="https://agentmods.dev/skills/larsboes/axon/secrets-guard"><img src="https://agentmods.dev/badge/skills/larsboes/axon/secrets-guard/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.
<a href="https://agentmods.dev/skills/larsboes/axon/secrets-guard"><img src="https://agentmods.dev/badge/skills/larsboes/axon/secrets-guard.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00151 | $0.01013 |
| Opus 5.5 | $0.00060 | $0.00405 |
| Sonnet 5.5 | $0.00030 | $0.00203 |
| Haiku 4.5 | $0.00015 | $0.00101 |
Grade A, and why
secrets-guard 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
source .env && curl -sS -H "Authorization: Bearer $SOME_API_KEY" https://api.example.com/... How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
secrets-guard (Claude Code)
Credentials must do their job without their values ever entering the conversation. Once a secret is in context it can leak into session files, logs, or provider requests. This skill is the workflow; enforcement is separate and already active:
- Managed policy —
tools/templates/claude-code/managed-settings.json(deployed to/etc/claude-code/managed-settings.json) denies reads of**/*.env,**/*.pem,~/.ssh,~/.aws,git-credentials,printenv,*_TOKEN*, etc., and denies ~20 secret env vars to the sandbox. You cannot relax it from a repo. If a command here is blocked, that is the floor working. - pi — the same protection is enforced as a tool-call extension (
Packs/security/extensions/ secrets-guard.ts); this skill is the Claude Code counterpart for the parts a policy can't teach.
The one rule
Never cat / read / grep / echo a secret. Feed it to the command that needs it via the
environment, so only the child process sees the value.
Patterns
Use a credential in a command — source the env file, then run; sourcing loads variables without printing them:
source .env && curl -sS -H "Authorization: Bearer $SOME_API_KEY" https://api.example.com/...
The value is in the subshell's env, never in your output. Do not echo "$SOME_API_KEY" to
"check" it — that defeats the point and is blocked.
Discover what a config needs without reading values — read the committed template, not the
real file (templates are safe; real .env is denied):
cat .env.example # or config.example.toml, etc. — placeholders only
A secret from Bitwarden/Vaultwarden — unlock, then let the command consume it; never bw get
into the transcript:
bw unlock # sets a session; the token is not a secret value
# then source a script that itself calls `bw get` and exports into env — you never see the value
Creating or rotating a secret — stop and hand off
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 · -4 tokens per session d249f28b3391
- 2mo ago Changed · +8 lines 0f51cd5ee04f
- 2mo ago First seen · 75 lines · 155 tokens per session scan A 5a3c2e705cf7
secrets-guard is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed 1mo ago), licensed MIT. It adds 151 tokens to every session and 1,013 once invoked, about $0.0006 per session on Opus 5.5. 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.
secrets-guard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| secrets-guardlarsboes/Axon | Skill | 1 | 1mo ago | MIT | A | 151 | Claude Code |
| ligandmpnnaipoch/open-science | Skill | 5.5k | today | Apache-2.0 | A | 100 | Claude Code, Codex |
| evo2aipoch/open-science | Skill | 5.5k | today | Apache-2.0 | A | 83 | Claude Code, Codex |
| create-agentPM-Shawn/Abu-Cowork | Skill | 419 | 3d ago | Apache-2.0 | A | 13 | Claude Code |
| content-monitorCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 16 | Claude Code, Codex |
| llm-wikiCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 27 | Claude Code, Codex |
| simplifyCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 24 | Claude Code, Codex |