agentmods.dev

write-probe

A small authenticated probe script for checking one successful request and one representative error against a real external service. It is temporary reference code and is not run during this step.

In plain words
What is it for?
Use it to prepare a service check with the correct request sequence, secret names, success case, and error case before recording the exchange.
Why use it?
It verifies the researched access pattern before implementation and keeps secrets scoped to the probe instead of exposing them through the process environment. It also prevents throwaway code from becoming part of the application.

Skill for Claude CodeCodex

11 27d ago A scan 28 tokens original MIT
View the source file nullhack/temple8
Install

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.

agentmods
npx agentmods add skills/nullhack/temple8/write-probe
Any agent
npx skills add nullhack/temple8 --skill write-probe
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 253 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00253
Opus 5 $0.00014 $0.00127
Sonnet 5 $0.00006 $0.00051
Haiku 4.5 $0.00003 $0.00025

Measured yesterday against content hash 1e1d7adced82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-probe 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 yesterday.

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.

.opencode/skills/write-probe/SKILL.md · 13 lines

What it actually says

Write Probe

  1. Load [[software-craft/external-fixtures]] — probe patterns and the kind-dispatch table.
  2. Translate the researched access shape into the real working call sequence. Cover one success path and at least one representative error path.
  3. Pull secrets from ~/.secrets/<project>.env via dotenv_values() — never load_dotenv() into os.environ (secrets stay scoped to the probe, off the process env); non-secret config (base URLs) comes from the workspace .env. Reference every secret by name; never print or log it. IF a secret the probe needs is not yet set up THEN instruct the user how to obtain and place it — do not create it. Per [[software-craft/secrets-and-config]].
  4. Keep the script throwaway — reference for the capture step and the later implementer. IF the package or tests could import it THEN move it out — it is never imported.
  5. Do not execute the script here; capturing the exchange is the next step's job.
Changes

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.

  1. yesterday First seen · 13 lines · 28 tokens per session scan A 1e1d7adced82

Subscribe to this mod's changes

write-probe is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 28 tokens to every session and 253 once invoked, about $0.0001 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 2026-08-30.

LanguagesSecurityTestingproject-templatepytestpythonpython-project-templatepython3uv
Related

Other skills, from other repositories

load-github-action-thread

Download retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request.

astral-sh/uv · 62 tokens

test-generator

Generate pytest test cases for Python functions and classes.

vstorm-co/pydantic-deepagents · 12 tokens

python-binance

Help developers use the python-binance library for trading on Binance. Use when code imports binance, references Client/AsyncClient, or asks about Binance API trading, market data, websockets, or account management.

sammchardy/python-binance · 47 tokens

itx:execute

Execute the plan for an issue (parent or subtask).

ric03uec/clawrium · 17 tokens

clawctl

Know the clawctl CLI and manage your Clawrium fleet (hosts, agents, providers, channels, integrations, skills, secrets).

ric03uec/clawrium · 31 tokens

create-playwright

Record a browser-session demo (MP4) using Playwright via a replay-first compile pipeline. A YAML spec drives the driver script, the recording, and the ElevenLabs voiceover — mirrors create-vhs for browser flows.

ric03uec/clawrium · 49 tokens