github-post-attribution

github-post-attribution is a skill for Claude Code, Codex from tomzx/agents. It costs 82 tokens per session (1,942 once invoked), scanned A, original, MIT.

A shared helper for identifying which agent skill produced text posted to GitHub and adding a link to that skill's source and the model used. GitHub is a code-hosting and collaboration service with issues and pull requests.

In plain words
What is it for?
Use it when another workflow posts issue comments, pull request comments, reviews, or issue descriptions through the GitHub CLI.
Why use it?
It makes automated GitHub comments and pull request text traceable to the exact skill version that created them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when another workflow posts issue comments, pull request comments, reviews, or issue descriptions through the GitHub CLI.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/github-post-attribution
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.

Any agent
npx skills add tomzx/agents --skill github-post-attribution
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code, 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 github-post-attribution

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/github-post-attribution/github.svg)](https://agentmods.dev/skills/tomzx/agents/github-post-attribution)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/github-post-attribution"><img src="https://agentmods.dev/badge/skills/tomzx/agents/github-post-attribution/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 github-post-attribution

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/github-post-attribution"><img src="https://agentmods.dev/badge/skills/tomzx/agents/github-post-attribution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,942 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 18
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 77
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 103
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00082 $0.01942
Opus 5.5 $0.00033 $0.00777
Sonnet 5.5 $0.00016 $0.00388
Haiku 4.5 $0.00008 $0.00194

Measured today against content hash 6640e6a71b52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-post-attribution 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 today.

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.

skills/github-post-attribution/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub post attribution (shared)

Skills that post content to GitHub should append a small footer: link to the invoking skill's SKILL.md at the current agents commit (the revision in use when the post was made), plus the model name that executed the skill.

When to use

  • Any gh or ghx command that creates or updates issue/PR text visible on GitHub.
  • Invoked by name from other skills (e.g. "follow skills/github-post-attribution/SKILL.md before posting").

Resolve repository root, commit, and GitHub base URL

REPO_ROOT = the directory that contains skills/ (the agents checkout). The path to this file is always known from the Read call that loaded it. Use it directly -- no additional filesystem exploration needed.

Every skill file lives at <REPO_ROOT>/skills/<SKILL_DIR>/SKILL.md. Resolve symlinks (e.g. ~/.agents/skills → ~/src/agents/skills) and capture all values in one call:

SKILL_MD_DIR=$(dirname "$(readlink -f /path/to/this/SKILL.md)")
REPO_ROOT=$(cd "$SKILL_MD_DIR" && git rev-parse --show-toplevel)
SKILL_COMMIT=$(cd "$REPO_ROOT" && git rev-parse HEAD)
SKILL_SHORT_SHA=${SKILL_COMMIT:0:7}
REMOTE_URL=$(cd "$REPO_ROOT" && git remote get-url origin)

Replace /path/to/this/SKILL.md with the absolute path used in the Read call. readlink -f resolves any symlinks before git sees the path, so --show-toplevel always returns the real repo root.

From REMOTE_URL, normalize to https://github.com/{owner}/{repo}:

  • [email protected]:owner/repo.git → https://github.com/owner/repo
  • https://github.com/owner/repo.git → https://github.com/owner/repo

Call that {BASE}.

Resolve model name

The model that executed the skill is identified by its short name (e.g. glm-5.1, claude-sonnet-4-20250514). The agent knows its own model at runtime from its environment. Set MODEL_NAME to the model's human-facing label:

MODEL_NAME="glm-5.1"  # replace with the actual model name at runtime

Read the full file on GitHub · 144 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. today Changed 6640e6a71b52
  2. 11d ago Changed · +2 lines 1220af46235a
  3. 22d ago Changed · +8 lines d0859e7d279e
  4. 24d ago Changed 0100687a8a2a
  5. 27d ago Changed · +3 tokens per session 91490701ec4e
  6. 1mo ago First seen · 134 lines · 79 tokens per session scan A 65d34961e002

Subscribe to this mod's changes

github-post-attribution is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,942 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.