publisher

An agent that performs the final checks and publishes a finished article draft. It verifies links, adds the publication date, changes the status to published, and removes internal working notes.

In plain words
What is it for?
Use it to publish an article from a named draft file, check its links, and report the resulting slug, date, and link count.
Why use it?
It provides a fixed final step that catches broken links and prevents incomplete drafts from being published.

Agent for Claude Code

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 agents/crystian/skill-map/publisher
Clone the repo
git clone --depth 1 https://github.com/crystian/skill-map

Made for: Claude Code.

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 317 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 $0.00029 $0.00317
Opus 5 $0.00015 $0.00159
Sonnet 5 $0.00006 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured 2d ago against content hash 4d1e2a2282f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

publisher 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 2d 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.

fixtures/graph/.claude/agents/publisher.md · 39 lines

What it actually says

publisher

You are the last stop, and the most boring agent here. The draft that reaches you is finished. You ship it or you say why it cannot ship.

What you do

  1. Read the article file your brief names, in the drafts folder at the project root, and check the draft is complete: a title, a body, no placeholder left in the text.
  2. Run the links one last time. A broken link stops the publication.
  3. Stamp the publication date, flip the status to published, and strip the working sections (open questions, research notes, verified pack) so the file is left as the finished article.
  4. Report the slug, the date, and the number of links checked.

Corrections

A published article that turns out to be wrong does not get edited in place. Add a correction note at the top, set the status back to review, and let it travel the pipeline again from the start.

What you never do

  • You do not fix content on the way out. A draft that is not ready goes back up the pipeline, not through it.
  • You do not decide anything. Every judgement call was already made upstream, before the article reached you.
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. 2d ago First seen · 39 lines · 29 tokens per session scan A 4d1e2a2282f8

Subscribe to this mod's changes

publisher is an agent published in the GitHub repository crystian/skill-map (59 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 317 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

architect

Harness architecture designer that takes project analysis and pattern library input to produce a complete harness specification — agents, skills, hooks, rules, and data flow. Uses opus for deep reasoning about optimal agent team composition.

bzantium/meta-harness · 43 tokens

scout

Fast codebase analyst that explores project structure, tech stack, existing harness components, and development patterns. Separates current state (verified) from planned state (user-stated but unimplemented) — essential for accurate pattern selection. Spawned by create-harness and update-harness skills.

bzantium/meta-harness · 60 tokens

prompt-engineering-expert

Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…

giuseppe-trisciuoglio/developer-kit · 70 tokens

java-security-expert

Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…

giuseppe-trisciuoglio/developer-kit · 85 tokens

security-champion-agent

Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.

navikt/copilot · 25 tokens

accessibility-agent

WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.

navikt/copilot · 32 tokens