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 skills/fabriqaai/specs.md/intent-capturenpx skills add fabriqaai/specs.md --skill intent-capturegit clone --depth 1 https://github.com/fabriqaai/specs.mdWrote 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/skills/fabriqaai/specs.md/intent-capture)<a href="https://agentmods.dev/skills/fabriqaai/specs.md/intent-capture"><img src="https://agentmods.dev/badge/skills/fabriqaai/specs.md/intent-capture.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00901 |
| Opus 5 | $0.00010 | $0.00451 |
| Sonnet 5 | $0.00004 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
intent-capture 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 6d 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
<degrees_of_freedom> HIGH — This is a creative, exploratory phase. Ask open-ended questions. Don't constrain prematurely. </degrees_of_freedom>
<question if="unclear who benefits">
Who is this for? Who will use this feature?
</question>
<question if="unclear problem">
What problem does this solve? What's painful today?
</question>
<question if="unclear scope">
What's the minimum that would be valuable? What can wait?
</question>
<question if="unclear constraints">
Any technical constraints? Existing systems to integrate with?
</question>
<question if="unclear success">
How will you know this is working? What does success look like?
</question>
**Goal**: {summarized goal}
**Users**: {who benefits}
**Problem**: {what pain this solves}
**Success Criteria**:
- {criterion 1}
- {criterion 2}
- {criterion 3}
**Constraints**:
- {constraint 1}
- {constraint 2}
Is this accurate? [Y/n/edit]
</output>
<check if="response == n or edit">
<action>Ask specific clarifying questions</action>
<goto step="3"/>
</check>
Saved to: .specs-fire/intents/{intent-id}/brief.md
---
Ready to break this into work items? [Y/n]
</output>
<check if="response == y">
<invoke_skill>work-item-decompose</invoke_skill>
</check>
<output_artifacts>
| Artifact | Location | Template |
|---|---|---|
| Intent Brief | .specs-fire/intents/{id}/brief.md |
./templates/brief.md.hbs |
| </output_artifacts> |
<success_criteria> User intent fully understood through dialogue Goal, users, problem clearly captured Success criteria defined Constraints identified Intent brief saved to correct location State.yaml updated with new intent </success_criteria>
What ships with it
1 file 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.
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.
- 6d ago First seen · 126 lines · 20 tokens per session scan A bd95ff68b08d
intent-capture is a skill published in the GitHub repository fabriqaai/specs.md (206 stars, last pushed 13d ago), licensed MIT. It adds 20 tokens to every session and 901 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 2026-08-30.
Other skills, from other repositories
acceptance-orchestrator-v2
Acceptance Orchestrator workflow skill. Use this skill when the user needs a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention and the operator should preserve the upstream workflow, copied support files…
acceptance-orchestrator
Acceptance Orchestrator workflow skill. Use this skill when the user needs a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention and the operator should preserve the upstream workflow, copied support files…
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.