A read-only local web dashboard for repositories that contain an OpenSpec folder. OpenSpec is a file-based way to track proposed software changes, their documents, and their tasks.

Use it to browse an OpenSpec project, answer which changes are active, inspect a change's artifacts and tasks, or start its local dashboard.

It lets you inspect work in progress without editing or archiving change files. Summary and change views make it easier to see project status and completion progress.

openspeccer — Skill for Claude Code and Codex by sammcj/agentic-coding

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 sammcj/agentic-coding --skill openspeccer

Clone the repo

git clone --depth 1 https://github.com/sammcj/agentic-coding

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sammcj/agentic-coding/openspeccer/github.svg)](https://agentmods.dev/skills/sammcj/agentic-coding/openspeccer)

Your own site

<a href="https://agentmods.dev/skills/sammcj/agentic-coding/openspeccer"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/openspeccer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sammcj/agentic-coding/openspeccer"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/openspeccer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 503 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.00503
Opus 5.5	$0.00024	$0.00201
Sonnet 5.5	$0.00012	$0.00101
Haiku 4.5	$0.00006	$0.00050

Measured 7d ago against content hash c97d1991a04e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openspeccer 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 7d ago.

The scan reads SKILL.md. This mod also ships 41 executable files (assets/web/app.js, assets/web/export.js, assets/web/lib.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/openspeccer/SKILL.md · 26 lines

What it actually says

openspeccer is a read-only local web dashboard for any repository holding an openspec/ directory. It is stdlib Python and needs no install. Run <this-skill-dir>/scripts/serve.py --help for every option.

Workflow

Create a task per step below, each with its completion criterion, then work through them.
Find the repo: pass the user's repo path, or omit it and the script searches upward from the current directory for openspec/.
For a status question ("what's in flight?"), run serve.py <repo> --summary and answer from its output. For one change's artifacts and tasks, use --change <slug>. --json prints the whole snapshot; send it to a file and read only what you need. Done once you have answered, with no server started.
If the user wants the dashboard, start serve.py <repo> as a background process. Done when a line containing serving <name> at <url> appears, or the process exits; on exit, report its stderr to the user.
Always give the user the URL. Pass --no-open in headless or remote sessions, and when re-running against a server that is already up.
To stop it, end the background process you started, using the PID or task handle you captured at launch.

Gotchas

Re-running for the same repo reuses the running server and prints already serving, so step 4 is safe to repeat.
A server you did not start (no handle from this session) belongs to the user. Leave it running.
The OpenSpec CLI is optional and only feeds the Schemas and Commands pages. Without it, only project schemas show and Commands is empty. For a CLI outside PATH, set OPENSPECCER_OPENSPEC_BIN.
Active changes from every git worktree are aggregated by default.
The page updates as files change, so there is nothing to refresh after editing artifacts.

Files

What ships with it

48 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.

7d ago Changed c97d1991a04e
11d ago First seen · 26 lines · 59 tokens per session scan A fe9d278fd148

Subscribe to this mod's changes

openspeccer is a skill published in the GitHub repository sammcj/agentic-coding (165 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 503 once invoked, about $0.0002 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 2026-10-09.

LLM Project management agentic agents ai cline copilot

ap-tasks

Use the agentproto shared task board — taskcreate, taskclaim (CAS with rev), tasklist, and taskupdate to coordinate parallel agents on one board, gate done with verify commands, and hand off work claimably. Trigger when coordinating parallel agents, splitting work across sessions, handing off tasks, or needing…

agentproto/ts · 70 tokens

pb-nested-orchestrator

Spawn a parent agent that spawns and supervises its own sub-agents, forming a two-level tree on the agentproto daemon. Trigger for delegation depth - 'agent that spawns sub-agents', 'two-level agent tree', 'let an agent orchestrate on its own'.

agentproto/ts · 64 tokens

supervise-long-missions

Route missions that outlive your attention — durable waiting, completion gates with retries, scheduled cron check-ins, shared task boards, spend tracking, and cleanup. Use when an agent works longer than one turn or you must not block on it. Triggers: supervise, long-running mission, check-in, non-blocking wait…

agentproto/ts · 74 tokens

openspeccer