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/Exponential-OS/prompt-engineering-in-actionWrote 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/plugins/exponential-os/prompt-engineering-in-action/co-dialectic)<a href="https://agentmods.dev/plugins/exponential-os/prompt-engineering-in-action/co-dialectic"><img src="https://agentmods.dev/badge/plugins/exponential-os/prompt-engineering-in-action/co-dialectic/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/plugins/exponential-os/prompt-engineering-in-action/co-dialectic"><img src="https://agentmods.dev/badge/plugins/exponential-os/prompt-engineering-in-action/co-dialectic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
co-dialectic 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 20d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What it installs
The manifest is a name and a version. 11 skills, 5 hooks travel with it, and installing the plugin installs all of them — 1,179 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill codi-handoff A 120 tokens
- Skill judge-panel A 120 tokens
- Skill teachme A 109 tokens
- Skill waky-waky A 76 tokens
- Skill codi-agents A 193 tokens
- Skill forage A 132 tokens
- Skill hallucination-detector A 85 tokens
- Skill unknown-unknown A 61 tokens
- Skill calibration-auditor A 61 tokens
- Skill co-dialectic-onboarding A 100 tokens
- Skill co-dialectic B 122 tokens
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook PreCompact A not measured
- Hook TaskCompleted A not measured
- Hook UserPromptSubmit A not measured
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.
- 20d ago Changed aba74c09d0d6
- 1mo ago Changed 5b9e0965602d
- 1mo ago Changed · +1 lines 862fc33121bd
- 1mo ago First seen · 38 lines scan A a4bd040744a4
co-dialectic is a plugin published in the GitHub repository Exponential-OS/prompt-engineering-in-action (10 stars, last pushed 20d ago), licensed AGPL-3.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
dory
Memory for coding agents: a strict-tree wiki, a findings ledger, a taskboard and usage-aware long runs, enforced by hooks.
ai-context-kit
Build reusable context files about you and your company for any AI tool (personal-context, company-context, refresh-context).
memory-kit
Persistent memory for Claude Code agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a…
spark
Search and use agents, skills, prompts and MCP connectors from the Spark marketplace.
logs-locally-plugin
Store and browse AI agent session logs locally with a SQLite database and web UI.
codies-memory
File-based two-tier memory system for AI agents. Agent-namespaced vaults with promotion pipelines, trust levels, CLI write commands, and explicit general read mode for vault-less notes. Gives any agent persistent memory across sessions.