symphony-trello: Skill for Codex

.agents/skills/publish-bugbash-issues/SKILL.md

publish-bugbash-issues is a skill for Codex from martin-francois/symphony-trello. It costs 44 tokens per session (1,495 once invoked), scanned A, original, Apache-2.0.

A publishing procedure for reviewed bug reports, where a bug bash is a structured search for software problems and GitHub issues are the reports used to track them.

In plain words
What is it for?
Reading reviewed local issue drafts, creating GitHub issues for unique confirmed bugs, and commenting on matching existing issues.
Why use it?
It prevents unreviewed findings from being posted and handles confirmed duplicates by adding cleaned reproduction details to existing issues.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions Codex; $skill-name invocation.

This is martin-francois/symphony-trello's own configuration. It tells Codex how to work on symphony-trello itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything symphony-trello configures →

Reuse

Borrowing it

Nothing to install: this file belongs to martin-francois/symphony-trello. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/martin-francois/symphony-trello/main/.agents/skills/publish-bugbash-issues/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/martin-francois/symphony-trello

Made for: Codex.

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 publish-bugbash-issues

README.md
[![agentmods](https://agentmods.dev/badge/skills/martin-francois/symphony-trello/publish-bugbash-issues/github.svg)](https://agentmods.dev/skills/martin-francois/symphony-trello/publish-bugbash-issues)
Your own site
<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/publish-bugbash-issues"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/publish-bugbash-issues/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.

agentmods 80×15 button for publish-bugbash-issues

Your own site · 80×15
<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/publish-bugbash-issues"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/publish-bugbash-issues.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,495 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 $0.00044 $0.01495
Opus 5 $0.00022 $0.00747
Sonnet 5 $0.00009 $0.00299
Haiku 4.5 $0.00004 $0.00150

Measured 10d ago against content hash c38eee95624a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

publish-bugbash-issues 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 10d 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/skills/publish-bugbash-issues/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish bug-bash issues

Use this skill only after a person has reviewed local issue drafts created by $live-bugbash and explicitly asks to post them to GitHub. The reviewer must also complete each selected draft's AI Assistance (if used) human-review confirmation field before publication.

Do not use this skill for bug discovery. Do not run Symphony. Do not create Trello boards. Do not run Codex app-server. Do not create GitHub sandbox repositories. This skill only reads local issue drafts and posts reviewed results to the target GitHub repository.

Implicit invocation is disabled in agents/openai.yaml; do not select this skill accidentally.

Normal command

/goal Use $publish-bugbash-issues for RUN_ID=live-bugbash-20260629T103000Z. I reviewed the drafts and approve posting them to martin-francois/symphony-trello.

Defaults

Unless explicitly overridden:

TARGET_REPO=martin-francois/symphony-trello
RUN_ROOT=target/live-bugbash/<RUN_ID>
DRAFT_DIR=target/live-bugbash/<RUN_ID>/issues
DUPLICATE_ACTION=comment-with-reproduction-details
LABEL_POLICY=use-existing-labels-only
PUBLISH_SELECTION=confirmed-only

Before reading drafts or writing publication metadata, validate RUN_ID as one safe path segment: ASCII letters, digits, ., _, and - only; not empty; not . or ..; no slash, backslash, control character, shell metacharacter, or percent-encoded separator. Resolve and normalize RUN_ROOT and DRAFT_DIR; DRAFT_DIR must stay under RUN_ROOT, and default run roots must stay under target/live-bugbash/. Stop if an override points outside the reviewed run-owned location.

Publication guard

Posting to TARGET_REPO is forbidden unless the goal affirmatively contains both:

  1. A clear posting instruction, such as post these drafts, publish these reviewed drafts, or create GitHub issues from these drafts.
  2. A human-review approval phrase, such as I reviewed the drafts or I have reviewed the drafts.

The skill name, default prompt text, or a denied phrase such as do not publish, do not comment, preview only, or dry run does not count as posting approval. If either signal is missing or negated, do not publish, do not comment, and explain the exact command the operator can use after reviewing the drafts. Never infer approval from the existence of issue drafts.

Read the full file on GitHub · 140 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 140 lines · 44 tokens per session scan A c38eee95624a

Subscribe to this mod's changes

publish-bugbash-issues is a skill published in the GitHub repository martin-francois/symphony-trello (2 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 1,495 once invoked, about $0.0002 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.