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 jscraik/Agent-Skills --skill workflow-guardrail-candidatesgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/workflow-guardrail-candidates)<a href="https://agentmods.dev/skills/jscraik/agent-skills/workflow-guardrail-candidates"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/workflow-guardrail-candidates/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/jscraik/agent-skills/workflow-guardrail-candidates"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/workflow-guardrail-candidates.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 | $0.00120 |
| Opus 5.5 | $0.00007 | $0.00048 |
| Sonnet 5.5 | $0.00003 | $0.00024 |
| Haiku 4.5 | $0.00002 | $0.00012 |
Grade A, and why
workflow-guardrail-candidates 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.
What it actually says
Workflow Guardrail Candidates
This directory is the runnable source root for the workflow-guardrail-candidates eval pack.
Layout
references/evals.yamlholds the claim-to-case routing and calibration expectations.evals/contains per-case task and criteria files.tessl.jsonmarks the staged project root for the eval runner.workflow-guardrail-candidates.jsonpreserves the canonical pack content used to generate the staged source.
What ships with it
25 files 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.
- evals/linear-p0-blocking/criteria.json 246 B
- evals/linear-p0-blocking/task.md 158 B
- evals/mise-uv-cache-drift/criteria.json 260 B
- evals/mise-uv-cache-drift/task.md 146 B
- evals/missing-closeout-evidence/criteria.json 266 B
- evals/missing-closeout-evidence/task.md 94 B
- evals/semgrep-anti-pattern/criteria.json 248 B
- evals/semgrep-anti-pattern/task.md 128 B
- evals/stale-feature-flag/criteria.json 259 B
- evals/stale-feature-flag/task.md 88 B
- evals/subagent-artifact-missing/criteria.json 266 B
- evals/subagent-artifact-missing/task.md 95 B
- references/contract.yaml 1.2 KB
- references/evals.yaml 2.4 KB
- references/scorer-calibration/examples.jsonl 1.1 KB
- references/scorer-calibration/manifest.json 771 B
- references/scorer-calibration/raw/concise-evidence-beats-verbose.json 183 B
- references/scorer-calibration/raw/copied-rubric-rejected.json 164 B
- references/scorer-calibration/raw/held-out-zero-to-one.json 177 B
- references/scorer-calibration/raw/obvious-correct-candidate-routing.json 181 B
- references/scorer-calibration/raw/obvious-wrong-no-evidence.json 162 B
- references/scorer-calibration/raw/skill-name-only-not-enough.json 168 B
- references/task-profile.json 1.2 KB
- tessl.json 173 B
- workflow-guardrail-candidates.json 3.1 KB
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 · 16 lines · 17 tokens per session scan A 9c066ed86e4c
workflow-guardrail-candidates is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 120 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 2026-09-13.
Other skills, from other repositories
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
hook-management
Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
spec-execution
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
tdd-enforcement
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.