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.
git clone --depth 1 https://github.com/formin/spec-kit-harnessWrote 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.
[](https://agentmods.dev/commands/formin/spec-kit-harness/speckit.harness.report)<a href="https://agentmods.dev/commands/formin/spec-kit-harness/speckit.harness.report"><img src="https://agentmods.dev/badge/commands/formin/spec-kit-harness/speckit.harness.report/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.
<a href="https://agentmods.dev/commands/formin/spec-kit-harness/speckit.harness.report"><img src="https://agentmods.dev/badge/commands/formin/spec-kit-harness/speckit.harness.report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00017 | $0.00953 |
| Opus 5 | $0.00009 | $0.00477 |
| Sonnet 5 | $0.00003 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
speckit.harness.report 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Report — Harness → Spec Kit Artifacts
Bridge the externalized harness state back into the standard spec-kit
artifact flow: synthesize the curated set, evidence links, and verification
records into the active feature's research.md, with an explicit coverage
table showing which requirements rest on verified evidence — the curated-set
quality measure of Harness-1 (arXiv:2606.02373), applied to specs.
Run this when exploration/verification is done (or budget is spent), before
/speckit.plan consumes the research.
User Input
$ARGUMENTS
Optional. A scope filter (only synthesize matching topics) or an alternative
output path. Default output: FEATURE_DIR/research.md.
Prerequisites
Resolve HARNESS_DIR as in /speckit.harness.init; require an initialized
harness. This command reads the FULL state files (it is the one command that
does) plus spec.md if present.
Steps
1. Load and cross-link
Read curated.md, evidence.md, verification.md, budget.md, and the
feature's spec.md (if present). Build the requirement → evidence map: for
each requirement / user story / open question in spec.md, collect curated
entries whose evidence Supports: field references it, plus any obvious
topical matches (mark the latter inferred).
2. Compute coverage
For each requirement, classify:
- covered-verified — ≥1 supporting curated entry whose claim is
verified. - covered-unverified — supporting evidence exists, none verified.
- contradicted — a supporting entry was
refuted. - uncovered — no evidence at all.
Coverage score = covered-verified / total requirements (report the raw fraction, e.g. "7/10 requirements verified").
3. Write research.md
If research.md exists, preserve any hand-written sections and replace only
the block between <!-- harness:begin --> and <!-- harness:end -->
(append the markers if absent). Inside the block:
<!-- harness:begin -->
## Research Summary (Research Harness)
Generated by /speckit.harness.report on <date>. State: specs/<feature>/harness/
### Verdict
<3–8 sentences: what the research established, citing evidence IDs>
### Requirement Coverage — <score>
| Requirement | Status | Evidence | Verification |
|-------------|--------|----------|--------------|
| FR-001 <short title> | covered-verified | E003, E007 | V002 (high) |
...
### Key Findings (curated set)
<curated entries grouped critical → low; each: finding, source pointer, verification status>
### Corrected Assumptions
<refuted claims: what was believed, what is actually true, record ID — or "none">
### Open Questions
<uncovered/unverifiable items + what would resolve each (access, budget, a decision)>
### Method & Budget
<1 line: actions spent per resource, stop reason, link to budget.md>
<!-- harness:end -->
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.
- 8d ago First seen · 110 lines · 17 tokens per session scan A a5127c875e1d
speckit.harness.report is a command published in the GitHub repository formin/spec-kit-harness (5 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 953 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.
Other commands, from other repositories
archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
sddp-implement-qc-loop
Command description: Run implement and QC in a continuous loop. Argument hint: [optional: feature directory or branch name] Command category: orchestration Prerequisites: spec, plan, tasks.
sddp-checklist
Command description: Generate and evaluate a requirements quality checklist. Argument hint: [optional: quality focus or feature context] Command category: feature-delivery Prerequisites: spec, plan.
sddp-plan
Command description: Create an implementation plan from the current feature specification. Argument hint: [optional: planning constraints or focus areas] Command category: feature-delivery Prerequisites: spec.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.
sddp-qc
Command description: Run quality control against the implemented feature. Argument hint: [optional: testing focus such as unit tests, security audit, requirements sync] Command category: feature-delivery Prerequisites: spec, plan, tasks, implementation:complete.