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 saemihemma/lead-producer-oss --skill workflow-specialist-hardeninggit clone --depth 1 https://github.com/saemihemma/lead-producer-ossWrote 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/saemihemma/lead-producer-oss/workflow-specialist-hardening)<a href="https://agentmods.dev/skills/saemihemma/lead-producer-oss/workflow-specialist-hardening"><img src="https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/workflow-specialist-hardening/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/saemihemma/lead-producer-oss/workflow-specialist-hardening"><img src="https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/workflow-specialist-hardening.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 | $0.00044 | $0.00779 |
| Opus 5 | $0.00022 | $0.00390 |
| Sonnet 5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
workflow-specialist-hardening 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specialist Hardening Workflow
Purpose
Push high-stakes work through repeated specialist review rounds until it is strong enough to ship, clearly blocked by a user decision, or no longer improving.
Use When
- User explicitly asks for hardening, deep specialist review, or "repeat until 9"
- Lead Producer judges the task high-stakes, hard-to-reverse, or launch-critical
- A first-pass recommendation needs adversarial tightening before acceptance
- Quality matters more than token thrift
Do NOT Use When
- A quick single-pass review is enough
- Broad repo or system understanding is still missing
- Root cause is still unknown and the task is debugging
- User only wants a lightweight recommendation
Round Setup
- Select exactly 3 reviewer slots from existing roles or teams.
- Reviewer mix must include:
- one primary domain owner
- one adversarial or constraint-checking perspective
- one complementary perspective likely to improve the result
- Reuse the existing index. Do not invent custom reviewers.
Evaluator Independence
- When the work being reviewed was generated by an AI agent, reviewers must not reuse the generation context. Shared context biases evaluation toward confirming the output.
- When feasible, at least one reviewer slot should verify by interacting with running artifacts (executing tests, navigating UI, calling endpoints) — not just reading code.
- If all three reviewers only read static output, note this as a confidence limitation in the round report.
- Prefer evaluators that produce falsifiable evidence (test output, error logs, metric diffs) over evaluators that produce opinions about code quality.
Review Loop
- Read the current state and any prior round deltas before scoring.
- Each reviewer returns:
- score from 1-10
- blockers
- highest-value improvements
What It IsWhat It Is NOT
- Merge overlaps and prioritize the improvements most likely to raise quality.
- Tighten the recommendation or artifact.
- Repeat while material improvements remain.
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 · 79 lines · 44 tokens per session scan A d13e0876fa05
workflow-specialist-hardening is a skill published in the GitHub repository saemihemma/lead-producer-oss (2 stars, last pushed 8d ago), licensed MIT. It adds 44 tokens to every session and 779 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…