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 chadixearth/graphyloop --skill secrets-hygienegit clone --depth 1 https://github.com/chadixearth/graphyloopWrote 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/chadixearth/graphyloop/secrets-hygiene)<a href="https://agentmods.dev/skills/chadixearth/graphyloop/secrets-hygiene"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/secrets-hygiene/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/chadixearth/graphyloop/secrets-hygiene"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/secrets-hygiene.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 | $0.00064 | $0.00821 |
| Opus 5 | $0.00032 | $0.00411 |
| Sonnet 5 | $0.00013 | $0.00164 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade B, and why
secrets-hygiene scanned grade B 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`<project>/.graphyloop/secrets.json`, chmod 600, git-ignored before the first How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Credential handling
A credential in a chat transcript is a leaked credential: transcripts are logged, summarized, and sometimes trained on. A credential in a committed file is worse — it is public and permanent. Both are avoidable with the same short procedure.
When to activate
- A task needs Supabase keys, a database URL, a Vercel/hosting token, or any API key.
- A tool call fails with "missing env var" / 401 / "invalid API key".
- Before any commit that touches
.env*, config, or CI files.
Procedure
- Check before asking.
secrets_status(orgraphyloop_secrets_status) reports, per provider, which keys exist, where each comes from (process env, graphyloop store,.envfile) and what is missing. It returns masks, never values. - Ask by NAME, never by paste. If a key is missing, tell the user the exact
key name and where to obtain it (e.g.
SUPABASE_SERVICE_ROLE_KEYfrom Settings → API). Then store it withsecrets_set— it lands in<project>/.graphyloop/secrets.json, chmod 600, git-ignored before the first write. Never ask them to paste it into the conversation. - Materialize it, do not read it.
env_synccopies stored values into the env file the framework actually reads (.env.localfor Next/Vite), adds the framework public alias for public keys only, and refreshes a values-free.env.example. Values move file-to-file; they never pass through your context. - Verify before using.
preflight(target=db|deploy|all) reports blockers and warnings. Clear the blockers first — a missing key found now costs nothing, found at integration it fails late and confusingly.
Hard rules
- Never print, echo, log or repeat a credential value — not in a report, not in a command you show the user, not in a test fixture, not in a commit message.
- Public vs secret is not cosmetic. A
SUPABASE_ANON_KEYmay reach the browser (RLS still applies). A service-role key bypasses RLS entirely: it must never appear in client code, and never behind aNEXT_PUBLIC_*/VITE_*name, because those are inlined into the browser bundle. - No credential in source. No literals, no "temporary" hardcoding, no keys in test files. Read from env; fail loudly with the key name when it is absent.
.env*must be git-ignored before it has content. If an env file exists and.gitignoredoes not cover it, fix that before any commit.- Rotate, do not hide. If a real credential was committed or pasted, say so immediately and tell the user to rotate it. Deleting the line does not un-leak it — the value stays in git history and in the transcript.
- Least privilege. Prefer a project-scoped token over an account-wide one; prefer anon + RLS over service-role; use service-role only in server-side code that needs it.
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.
- 5d ago First seen · 60 lines · 64 tokens per session scan B f20dbb87f5fd
secrets-hygiene is a skill published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 23d ago), licensed MIT. It adds 64 tokens to every session and 821 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agf
Find local coding-agent sessions, inspect bounded metadata or summaries, and prepare a read-only resume plan with AGF. Use for finding prior work across agent CLIs, not for executing agents, deleting sessions, or reading full transcripts.
aikito
Install, configure, and operate Aikito workspaces, including memory, skills, project resources, MCP servers, subagents, adoption, synchronization, and status verification.
durable-memory
Git-versioned memory stored in the Aikito workspace, separate from any Agent's built-in memory. Use to search, retrieve, or persist cross-project and project-scoped durable knowledge, historical decisions, user preferences, or verified architecture constraints.
kirby-collections-and-navigation
Builds Kirby listings, pagination, search, filtering/sorting/grouping, and navigation menus. Use when implementing collection logic in templates/controllers/snippets.
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.
kirby-headless-api
Exposes Kirby content to headless clients using the API, KQL, and JSON representations. Use when building API endpoints, KQL queries, or headless frontends.