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 skills add fabriqaai/specs.md --skill statusgit 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/status)<a href="https://agentmods.dev/skills/fabriqaai/specs.md/status"><img src="https://agentmods.dev/badge/skills/fabriqaai/specs.md/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.
<a href="https://agentmods.dev/skills/fabriqaai/specs.md/status"><img src="https://agentmods.dev/badge/skills/fabriqaai/specs.md/status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 84 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00019 | $0.05552 |
| Opus 5.5 | $0.00008 | $0.02221 |
| Sonnet 5.5 | $0.00004 | $0.01110 |
| Haiku 4.5 | $0.00002 | $0.00555 |
Grade A, and why
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 1mo 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 — 697 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<degrees_of_freedom> LOW — Report facts accurately. Never auto-fix without user confirmation. </degrees_of_freedom>
**Project**: {project.name}
**Workspace**: {workspace.type} / {workspace.structure}
**Autonomy**: {workspace.autonomy_bias}
**Version**: {project.fire_version}
## Intents
{for each intent}
### {intent.title} [{intent.status}]
| Work Item | Status | Complexity | Mode |
|-----------|--------|------------|------|
{for each work_item}
| {title} | {status} | {complexity} | {mode} |
{/for}
{/for}
## Active Runs
{if runs.active is array and has items}
{for each active_run in runs.active}
- **Run**: {active_run.id} | **Scope**: {active_run.scope}
- **Current Item**: {active_run.current_item}
- **Started**: {active_run.started}
{/for}
{else if active_run exists (legacy singular)}
- **Run**: {active_run.id}
- **Work Item**: {active_run.work_item}
- **Started**: {active_run.started}
{else}
No active run.
{/if}
## Quick Stats
- Intents: {total_intents} ({completed_intents} completed)
- Work Items: {total_work_items} ({completed_work_items} completed)
- Runs: {total_runs} completed
</output>
<substep n="3a" title="Scan Intents">
<action>Glob: .specs-fire/intents/*/brief.md</action>
<action>Extract intent IDs from directory names</action>
<action>Store as: intents_on_disk[]</action>
</substep>
<substep n="3b" title="Scan Work Items">
<action>Glob: .specs-fire/intents/*/work-items/*.md</action>
<action>Exclude design docs (*-design.md)</action>
<action>Extract work item IDs and parent intents</action>
<action>Store as: work_items_on_disk[]</action>
</substep>
<substep n="3c" title="Scan Runs">
<action>Glob: .specs-fire/runs/run-*/run.md</action>
<action>Extract run IDs from directory names</action>
<action>For each run, check which artifacts exist:</action>
<substep>plan.md, test-report.md, review-report.md, walkthrough.md</substep>
<action>Store as: runs_on_disk[] with artifact_flags</action>
</substep>
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.
- 1mo ago First seen · 697 lines · 19 tokens per session scan A 739c72fd01a8
status is a skill published in the GitHub repository fabriqaai/specs.md (219 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 5,552 once invoked, about $0.0001 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 2026-08-30.
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…
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…