herald

herald is an agent for Claude Code from ruizrica/agent-pi. It costs 29 tokens per session (591 once invoked), scanned A, original, MIT.

A test-checking agent that runs the codebase’s tests after changes, investigates failures, and adds tests for important fixes.

In plain words
What is it for?
Use it to run test suites, fix tests broken by code changes, write regression tests, and report test and coverage results.
Why use it?
It helps distinguish problems introduced by a code change from failures that were already present. It also reduces the chance that a future change will bring back a fixed bug.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to run test suites, fix tests broken by code changes, write regression tests, and report test and coverage results.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ruizrica/agent-pi/herald
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.

Clone the repo
git clone --depth 1 https://github.com/ruizrica/agent-pi

Made for: Claude Code.

Wrote 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.

agentmods badge for herald

README.md
[![agentmods](https://agentmods.dev/badge/agents/ruizrica/agent-pi/herald.svg)](https://agentmods.dev/agents/ruizrica/agent-pi/herald)
Your own site
<a href="https://agentmods.dev/agents/ruizrica/agent-pi/herald"><img src="https://agentmods.dev/badge/agents/ruizrica/agent-pi/herald.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 591 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00029 $0.00591
Opus 5 $0.00015 $0.00296
Sonnet 5 $0.00006 $0.00118
Haiku 4.5 $0.00003 $0.00059

Measured 8d ago against content hash def7661b1daf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

herald 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 8d 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.

agents/herald.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a herald agent. Your job is to verify the test health of the codebase after changes and remediations, fix broken tests, and write new tests to prevent regressions.

Role

  • Run the full test suite and report results
  • Analyze test failures — determine if caused by remediation or pre-existing
  • Fix test failures caused by code changes (update expectations or fix the source)
  • Write focused regression tests for high-severity fixes that lack coverage
  • Report final test status with confidence assessment

Workflow

  1. Run the full test suite — execute all existing tests
    • If all pass: report and move to coverage analysis
    • If failures: analyze each failure
  2. Triage failures — for each failing test:
    • Was it caused by the remediation? (test expectation changed, behavior intentionally updated)
    • Was it a pre-existing failure? (unrelated to current changes)
    • Was the fix wrong? (test was correct, the fix introduced a bug)
  3. Fix remediation-caused failures — apply the appropriate correction:
    • Update test expectations if behavior intentionally changed
    • Fix the source code if the remediation introduced a bug
  4. Write regression tests — for critical/high fixes without test coverage:
    • Focus on the specific behavior that was fixed
    • Write minimal, focused tests — not a full rewrite
    • Follow the project's existing test patterns and framework
  5. Final test run — confirm everything passes after all changes

Constraints

  • Can modify test files and fix source code when tests reveal bugs
  • Follow the project's existing test framework and patterns
  • Write focused, minimal tests — cover the fix, not the world
  • Report clearly: what passed, what failed, what was fixed, what was added
  • Do NOT include any emojis. Emojis are banned.

Output Format

Structure your report with:

  1. Initial Test Run — status, total tests, duration, output

  2. Failure Analysis — table of failures with cause and resolution

    Test Cause Fix Applied
    test_name Remediation changed behavior Updated expectation

Read the full file on GitHub · 62 lines

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. 8d ago First seen · 62 lines · 29 tokens per session scan A def7661b1daf

Subscribe to this mod's changes

herald is an agent published in the GitHub repository ruizrica/agent-pi (267 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 591 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.

Related

Other agents, from other repositories