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.
npx agentmods add commands/ghosteken/agent-harness/specgit clone --depth 1 https://github.com/Ghosteken/agent-harnessWhat 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 | $0.00012 | $0.00318 |
| Opus 5 | $0.00006 | $0.00159 |
| Sonnet 5 | $0.00002 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
spec 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.
What it actually says
Invoke the agent-harness:spec-driven-development skill.
Begin by understanding what the user wants to build. Ask clarifying questions about:
- The objective and target users
- Core features and acceptance criteria
- Tech stack preferences and constraints
- Known boundaries (what to always do, ask first about, and never do)
Whenever a clarifying question or open question has a small set of distinct answers (a choice between approaches, yes/no, pick-one-of-N), ask it with the AskUserQuestion tool instead of printing it as text — including the "Open Questions" checkpoint before implementation starts. Only fall back to plain text for questions that genuinely need a freeform answer.
Then generate a structured spec covering all six core areas: objective, commands, project structure, code style, testing strategy, and boundaries.
Save every spec under docs/specs/<feature-slug>/SPEC.md. If docs/, docs/specs/, or the feature's subfolder don't exist yet, create them — that's the standard home for specs in this project, not the project root. Check whether a spec folder for this feature already exists before writing — if so, confirm with the user whether to update it in place or create a new one (e.g. docs/specs/<feature-slug>-2/SPEC.md). Never overwrite an unrelated existing spec by defaulting to a generic root-level SPEC.md. Confirm the chosen path and content with the user before proceeding.
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.
- 2d ago First seen · 18 lines · 12 tokens per session scan A 71a1aaabd782
spec is a command published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 16d ago), licensed MIT. It adds 12 tokens to every session and 318 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
build
Run full verification pipeline.
insights
Surface patterns from your pro-workflow learnings and session history.
blackboard
Read or write a Network-AI blackboard key (shared multi-agent state).
cost-tracker
Track session costs, understand token spend, and get optimization tips.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
triage-issues
Launch the Issue Triage Agent (Haiku) to categorize and prioritize GitHub issues.