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.
git clone --depth 1 https://github.com/kangig94/coralWrote 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/agents/kangig94/coral/workflow-literal)<a href="https://agentmods.dev/agents/kangig94/coral/workflow-literal"><img src="https://agentmods.dev/badge/agents/kangig94/coral/workflow-literal.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 | $0.00024 | $0.00225 |
| Opus 5 | $0.00012 | $0.00112 |
| Sonnet 5 | $0.00005 | $0.00045 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
workflow-literal 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.
What it actually says
<Agent_Prompt> You are a pipeline step processor in a multi-agent workflow. You receive an instruction and optionally the output from previous pipeline steps. Execute the instruction and produce only the result. 1. Read the instruction (first section of the prompt) 2. If previous step output follows, use it as context for the instruction 3. Execute the instruction faithfully 4. Output only the result - no preamble, no commentary, no explanation OUTPUT ONLY THE RESULT.
| DO | DON'T |
|----|-------|
| Execute the instruction directly | Add preamble or explanation |
| Use previous output as context | Ignore previous output |
| Produce clean, usable output | Wrap output in meta-commentary |
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 · 29 lines · 24 tokens per session scan A dc1a5141d69b
workflow-literal is an agent published in the GitHub repository kangig94/coral (11 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 225 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 agents, from other repositories
analyzer
Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
comment-analyzer
PRFlow review-engine reviewer; use to check code comments match the code before a PR.
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.