speckit.harness.status

speckit.harness.status is a command for Claude Code from formin/spec-kit-harness. It costs 16 tokens per session (834 once invoked), scanned A, original, MIT.

A read-only status command for a research harness, meaning the files and rules used to track an ongoing research effort. It displays a limited snapshot of budgets, missions, recent actions, and the most important stored findings.

In plain words
What is it for?
Use it at the start of a session, or before deciding whether to investigate further, to inspect the harness state and optionally filter or expand the displayed information.
Why use it?
It lets an agent resume work from a compact current view instead of rereading complete transcripts or large files. It also shows the recommended next action within the remaining budget.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it at the start of a session, or before deciding whether to investigate further, to inspect the harness state and optionally filter or expand the displayed information.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/formin/spec-kit-harness/speckit.harness.status
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.

Clone the repo
git clone --depth 1 https://github.com/formin/spec-kit-harness

Made for: Claude Code.

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 speckit.harness.status

README.md
[![agentmods](https://agentmods.dev/badge/commands/formin/spec-kit-harness/speckit.harness.status/github.svg)](https://agentmods.dev/commands/formin/spec-kit-harness/speckit.harness.status)
Your own site
<a href="https://agentmods.dev/commands/formin/spec-kit-harness/speckit.harness.status"><img src="https://agentmods.dev/badge/commands/formin/spec-kit-harness/speckit.harness.status/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 speckit.harness.status

Your own site · 80×15
<a href="https://agentmods.dev/commands/formin/spec-kit-harness/speckit.harness.status"><img src="https://agentmods.dev/badge/commands/formin/spec-kit-harness/speckit.harness.status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 834 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 $0.00016 $0.00834
Opus 5 $0.00008 $0.00417
Sonnet 5 $0.00003 $0.00167
Haiku 4.5 $0.00002 $0.00083

Measured 8d ago against content hash ad1e83a4b389, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

speckit.harness.status 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 8d 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.

commands/speckit.harness.status.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Status — Budget-Aware Context Rendering

Render the externalized harness state as a compact working slice. This is the Harness-1 (arXiv:2606.02373) "budget-aware context rendering" step exposed as a command: instead of re-reading transcripts or whole files, the agent (and the user) get a bounded snapshot that is sufficient to decide the next action.

Run it at any time — especially at the start of a fresh session to resume research with zero context carried over, or before deciding whether more exploration is worth the budget.

This command is read-only: it writes nothing and consumes no budget.

User Input

$ARGUMENTS

Optional. full renders larger slices (3× the configured sizes); a topic string filters curated/candidate rows to those matching it.

Steps

1. Locate state

Resolve HARNESS_DIR as in /speckit.harness.init. If no harness exists, say so and point to /speckit.harness.init — do not create anything.

2. Load slices only

Read configuration for slice sizes (rendering.*), then load:

  • budget.md — mission(s), budget table, stop conditions, last 5 action-log rows.
  • curated.md — top curated_slice entries by importance (critical first); count the rest.
  • candidates.md — up to candidates_slice rows with status new/inspected; count the rest.
  • verification.md — all refuted rows, plus counts by verdict; list critical curated entries lacking a verified record.
  • observations.md — last observations_slice entries.

Do not read evidence.md bodies, spec/plan files, or anything beyond the slices. Keep the rendered output within the configured context_tokens cap; truncate lowest-importance material first and say what was truncated.

3. Render the snapshot

# Harness Status — <feature> (<date>)

**Mission**: <mission lines>

**Budget**: searches <r>/<b> · inspections <r>/<b> · verifications <r>/<b> remaining

**Curated set** (<shown>/<total>, cap <cap>):
| ID | Importance | Finding | Verified? |
...

**Open frontier** (<shown>/<total> candidates): ...

**Verification**: <n> verified · <n> refuted · <n> unverifiable
⚠ Unverified critical claims: <list or "none">
⚠ Refuted (do not rely on): <list or "none">

**Recent activity**: <observation slice, one line each>

Read the full file on GitHub · 94 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. 8d ago First seen · 94 lines · 16 tokens per session scan A ad1e83a4b389

Subscribe to this mod's changes

speckit.harness.status is a command published in the GitHub repository formin/spec-kit-harness (5 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 834 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 2026-08-31.