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 instructions/jentic/jentic-one/agents-mdgit clone --depth 1 https://github.com/jentic/jentic-oneWrote 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/instructions/jentic/jentic-one/agents-md)<a href="https://agentmods.dev/instructions/jentic/jentic-one/agents-md"><img src="https://agentmods.dev/badge/instructions/jentic/jentic-one/agents-md.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 | $0.01322 | $0.01322 |
| Opus 5 | $0.00661 | $0.00661 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade C, and why
jentic-one AGENTS.md scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh` How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
If
.rules/exists, read.rules/AGENTS.mdand use it instead of this file. Otherwise use the guidance below.
Using Jentic One (not changing it)
If your task is to install Jentic One and connect an agent to it, follow this section. The rest of this file is for changing the codebase.
Install. Two supported paths:
- Signed release binary, from https://github.com/jentic/jentic-one/releases/latest. Verify
against
checksums.txt(signature:checksums.txt.sig, certificate:checksums.txt.pem), then runjenticctl install. Prefer this path: it is verifiable before execution, and a sandboxed agent will usually be refused permission to pipe a script to a shell. - Bootstrap script:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shThis downloads a Go toolchain if none is present, clones this repository, buildsjenticctlandjentic, then runsjenticctl install. SetJENTIC_NO_INSTALL=1to stop after the binaries are installed — do that on the agent machine, which needs only the binaries, not a second deployment.
Run Jentic One on a different machine from the agent. An agent running as the same OS user
can read the credential database and encryption key from disk, whatever the API-level controls
allow. See docs/security/hardening.md before using real credentials.
Register and reach a first call:
jentic setup --url <control-plane URL>creates the agent identity, waits for an operator to approve it, and installs the agent skill. (jentic register --url …is the registration-only path — identity only, no skills; without--urlboth fall back to the configured base URL orhttp://127.0.0.1:8000, and prompt for it on an interactive terminal.) Report the wait to the user: on a single-operator install they are the operator, and they approve the agent in the UI at/app.- If no admin account exists yet, point the user to
/setup(browser) orjenticctl setup(terminal). This is a one-time step. - Import an API from https://github.com/jentic/jentic-public-apis (e.g.
httpbin.org, used in step 6), or register a private OpenAPI description of the user's own service. - Store a credential for that API, once. It is encrypted at rest and is never returned.
- Request access:
jentic access request --toolkit <vendor/name>files a reviewable request; granting is always a human action. The operator binds the agent to a toolkit — access is default-deny, and a rule-less binding still blocks everything. jentic execute GET:https://httpbin.org/get --jsonruns a call through the Broker with the credential injected. Giveexecutethe operation's full upstream URL (as returned byjentic search/jentic inspect) or its operation_id — the Broker is a forward proxy, not a path router.
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.
- 4d ago First seen · 97 lines · 1,322 tokens per session scan C 48d068e17307
jentic-one AGENTS.md is an instructions file published in the GitHub repository jentic/jentic-one (173 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,322 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
zeroclaw AGENTS.md
AGENTS.md instructions for zeroclaw-labs/zeroclaw, covering agents.md - zeroclaw, single source of truth, safety and privacy, working rules and user-facing text.
zeroclaw CLAUDE.md
Claude Code instructions for zeroclaw-labs/zeroclaw, covering claude.md — zeroclaw (claude code), claude code settings, hooks and slash commands.
lobu AGENTS.md
Instructions for lobu-ai/lobu, covering repo map, unrecoverable — never do these, facts you cannot derive, ship a change and how to work.
lobu CLAUDE.md
Instructions for lobu-ai/lobu, a project described as: Open-source control plane and runtime for organisational agents: shared company context, isolated execution, approvals and MCP.
gossipcat-ai CLAUDE.md
Claude Code instructions for gossipcat-ai/gossipcat-ai, covering claude.md, gossipcat — multi-agent orchestration, your role, agent accuracy — skill development and scoped agent contract.
maidan CLAUDE.md
Instructions for david-engelmann/maidan, covering agent guide, 30-second orientation, read order, the cluster model in one paragraph and pr workflow (the short version).