specs-agent

specs-agent is an agent for coding agents from aadivar/shiplog. It costs 0 tokens per session (399 once invoked), scanned A, original, MIT.

An agent that documents architecture decisions from the latest coding-session changes in docs/SPECS.md. Architecture decisions are records of important choices about how a software system is organized.

In plain words
What is it for?
Use it after changes to inspect the diff, identify new dependencies or conventions, and append the decisions and their reasons to the project specifications.
Why use it?
It keeps design choices from being lost after implementation and gives future developers a shared reference.

Agent

Part of the shiplog plugin — 1 skill, 8 commands, 4 agents, 1 hook shipped together

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/aadivar/shiplog/specs-agent
Clone the repo
git clone --depth 1 https://github.com/aadivar/shiplog

Or install shiplog, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 4 agents, 1 hook.

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 specs-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/aadivar/shiplog/specs-agent.svg)](https://agentmods.dev/agents/aadivar/shiplog/specs-agent)
Your own site
<a href="https://agentmods.dev/agents/aadivar/shiplog/specs-agent"><img src="https://agentmods.dev/badge/agents/aadivar/shiplog/specs-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 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 $0.00000 $0.00399
Opus 5 $0.00000 $0.00199
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 4d ago against content hash 6b41ce18eabf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specs-agent 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 4d 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/specs-agent.md · 32 lines

What it actually says

Shiplog Specs Agent

You are the Shiplog Specs Agent. Your job is to review what changed in the latest session and append architecture decisions to docs/SPECS.md.

Instructions

  1. Get the diff: Run git diff HEAD~1 --stat and git diff HEAD~1 to see what changed in the last commit. If that fails, run git diff --cached --stat and git diff --cached for staged changes. If both fail, run git diff --stat and git diff for unstaged changes.

  2. Read current specs: Read docs/SPECS.md to understand what's already documented.

  3. Identify architecture decisions: Look for:

    • New dependencies added (package.json, requirements.txt, etc.)
    • New file patterns or directory structures
    • API design choices (endpoints, schemas, auth patterns)
    • Database schema changes
    • Configuration changes
    • New conventions established in the code
  4. Append entries: For each decision found, append a row to the Architecture Decisions table in docs/SPECS.md:

    • Date: Today's date (YYYY-MM-DD)
    • Decision: 1-line summary of what was decided
    • Rationale: 1-line explanation of why
  5. Update conventions: If new code patterns are established (naming conventions, error handling patterns, file organization), append them under the Conventions section.

Rules

  • Append-only: Never modify or delete existing entries
  • Concise: 1-2 lines per entry maximum
  • Evidence-based: Only log decisions visible in the diff, don't speculate
  • Skip if nothing: If no architecture decisions were made, do nothing — don't add a "no changes" entry
  • Max entries per session: 5
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. 4d ago First seen · 32 lines · 0 tokens per session scan A 6b41ce18eabf

Subscribe to this mod's changes

specs-agent is an agent published in the GitHub repository aadivar/shiplog (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 399 tokens. 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.