Borrowing it
Nothing to install: this file belongs to EndogenAI/dogma. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EndogenAI/dogma/main/.github/skills/research-epic-planning/SKILL.mdgit clone --depth 1 https://github.com/EndogenAI/dogmaWrote 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/endogenai/dogma/research-epic-planning)<a href="https://agentmods.dev/skills/endogenai/dogma/research-epic-planning"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/research-epic-planning/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/endogenai/dogma/research-epic-planning"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/research-epic-planning.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 | $0.00132 | $0.02229 |
| Opus 5.5 | $0.00053 | $0.00892 |
| Sonnet 5.5 | $0.00026 | $0.00446 |
| Haiku 4.5 | $0.00013 | $0.00223 |
Grade A, and why
research-epic-planning 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 2mo 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Epic Planning
This skill enacts the Endogenous-First axiom from MANIFESTO.md: before planning begins, the agent reads all prior research, existing issues, and endogenous sources — so the plan is scaffolded from known context, not guessed. Epic planning discipline is governed by AGENTS.md § Agent Communication → docs/plans/. Read both documents before deviating from any step.
Canonical template: docs/plans/2026-03-08-value-encoding-fidelity.md — the reference implementation of a well-formed research epic workplan.
1. When to Use This Skill
Use this skill when the session involves:
| Criterion | Threshold |
|---|---|
| Number of related research issues | ≥ 3 |
| Issues span multiple execution phases or agent types | Yes |
| A milestone exists or is being created | Yes |
| Future sessions need to pick up phases independently | Yes |
For a single research issue, use the deep-research-sprint skill instead.
2. Pre-Planning: Endogenous Source Gathering
Before writing a single line of the workplan, run this sequence. Record findings in the scratchpad under ## Epic Planning — Scope Analysis.
2.1 Read All Relevant Issues
# Get all open issues (with labels for effort/priority/type)
gh issue list --state open --json number,title,labels --limit 80
# Read the anchor issue or each milestone issue in full
gh issue view <ISSUE_NUMBER>
For each issue, note:
- Core research question or deliverable
- Stated dependencies (
Depends on:lines in body) - Effort label:
xs/s/m/l/xl - Type:
research/feature/chore/docs
2.2 Survey Existing Research Docs
ls docs/research/
Identify which docs/research/*.md docs are the primary endogenous sources. Read the abstract/executive summary of each relevant doc. Do not bulk-read the full corpus — targeted retrieval only.
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.
- 2mo ago First seen · 224 lines · 132 tokens per session scan A 0cacb3b11eae
research-epic-planning is a skill published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 132 tokens to every session and 2,229 once invoked, about $0.0005 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 2026-08-31.
research-epic-planning compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research-epic-planningEndogenAI/dogma | Skill | 2 | 2mo ago | Apache-2.0 | A | 132 | Claude Code |
| custom-brand-designKbWen/agentic-os | Skill | 227 | 4d ago | MIT | A | 23 | Claude Code, Codex |
| air-blackbox-sales-agentairblackbox/airblackbox | Skill | 25 | 4d ago | Apache-2.0 | A | 248 | Claude Code, Codex |
| interpret-resultsairblackbox/airblackbox | Skill | 25 | 4d ago | Apache-2.0 | A | 49 | Claude Code |
| compliance-scanairblackbox/airblackbox | Skill | 25 | 4d ago | Apache-2.0 | A | 51 | Claude Code |
| nio-external-scorecore0-io/nio | Skill | 20 | 13d ago | Apache-2.0 | A | 97 | Claude Code |
| nio-scancore0-io/nio | Skill | 20 | 13d ago | Apache-2.0 | A | 81 | Claude Code |