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/srikanthmx/hermes-cli-orchestrator/catalog-refreshnpx skills add srikanthmx/hermes-cli-orchestrator --skill catalog-refreshgit clone --depth 1 https://github.com/srikanthmx/hermes-cli-orchestratorWrote 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/srikanthmx/hermes-cli-orchestrator/catalog-refresh)<a href="https://agentmods.dev/skills/srikanthmx/hermes-cli-orchestrator/catalog-refresh"><img src="https://agentmods.dev/badge/skills/srikanthmx/hermes-cli-orchestrator/catalog-refresh.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 5.1 | $0.00062 | $0.01097 |
| Opus 5 | $0.00031 | $0.00549 |
| Sonnet 5 | $0.00012 | $0.00219 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
catalog-refresh 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 6d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catalog Refresh — keep the CLI Governor current with the market
The plugin's value is a living catalog. Models and CLIs change monthly (new free tiers, dead ones, new agents). This skill researches what's out there, adds/configures the ones that fit, verifies them, and removes dead weight.
Where the catalog lives
- CLIs →
DEFAULT_CATALOGindashboard/plugin_api.py. - Model providers →
PROVIDERS_CATALOGin the same file. - Media backends →
MEDIA_CATALOGin the same file. - Get-key links → each provider/media
signupfield + theENV_KEY_URLmap indashboard/dist/index.js. - Delegation workers →
DELEGATE_ARGV+CODING_PRIORITYin__init__.py, and_DELEGATE_PRIORITY+_CLI_TEST_ARGVinplugin_api.py. - Users can also override/extend via
~/.hermes/cli-orchestrator/catalog.json(merged by id; entries there show ascustom).
Step 1 — Research (web)
Search for the current state (use the real month/year):
- AI coding/agent CLIs with a headless / non-interactive mode (e.g.
... -p,... run,... exec). - Free / free-tier / trial-credit / cheap LLM providers usable as a Hermes model provider (API key or OAuth). Capture per candidate: exact binary name, install command(s) per OS, headless one-shot invocation, auth method (OAuth login vs API-key env var), get-key URL, and free-tier limits / cooldown.
Step 2 — Decide: ADD, KEEP, or REMOVE
Add a CLI only if it has a clean non-interactive headless mode (so it can be a cli_delegate worker). If it's interactive-only, it can still be catalogued for detection but NOT added to DELEGATE_ARGV.
Add a provider if it's free/cheap/trial and the user can obtain a key/OAuth. Include tier, signup, limit.
Remove / demote (prune criteria) — this is deliberate, keep the catalog lean:
- No headless mode → useless as a governed delegate worker (interactive-only pair-programmers).
- Dead free tier (e.g. Gemini CLI's individual tier ended) → mark legacy or remove.
- Superseded by a better tool for the same job.
- Heavy per-tool provider config with no governance benefit over what's already covered.
- Example already actioned:
aiderremoved — it's an interactive, git-repo-centric pair-programmer, not a clean stateless delegation worker for this plugin's use case.
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.
- 6d ago First seen · 58 lines · 62 tokens per session scan A 399bd06117e7
catalog-refresh is a skill published in the GitHub repository srikanthmx/hermes-cli-orchestrator (12 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,097 once invoked, about $0.0003 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.
Other skills, from other repositories
evolve
Start or monitor an evolutionary development loop.
hunt-auth-bypass
Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024)…
m365-entra-attack
Microsoft 365 / Entra ID red-team attack chain — current 2026 reality. AADSTS code reference, user enumeration vectors (with hardening status), Smart Lockout math, Conditional Access bypass options, ROPC + SAML SSO browser flow, Burp/Playwright templates. Built from authorized red-team work where ROPC spray surfaced…
password-spray-methodology
End-to-end password spray playbook. User enumeration, lockout detection, password pattern generation, spray execution across all protocols, error code differentials, and engagement discipline. Unifies M365/Entra, Okta, Exchange, Kerberos, SharePoint, XMLRPC, OIDC, and AD SMB/WinRM spraying into one methodology.
subdomain-enumeration
Map subdomains via crt.sh and subfinder at recon kickoff.
cache-attack
Poison CDN cache or deceive when X-Cache header is detected.