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/prompt-archaeology/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/prompt-archaeology)<a href="https://agentmods.dev/skills/endogenai/dogma/prompt-archaeology"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/prompt-archaeology/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/prompt-archaeology"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/prompt-archaeology.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 | $0.00131 | $0.02760 |
| Opus 5.5 | $0.00052 | $0.01104 |
| Sonnet 5.5 | $0.00026 | $0.00552 |
| Haiku 4.5 | $0.00013 | $0.00276 |
Grade A, and why
prompt-archaeology 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Archaeology
Governing Axiom
This skill enacts the Endogenous-First axiom from MANIFESTO.md:
Session artifacts — scratchpads, commit messages, issue comments, session summaries — are endogenous knowledge. Mining them before reaching outward satisfies the axiom that existing system knowledge must be exhausted before generating new tokens.
It also enacts the Programmatic-First principle from AGENTS.md:
Constraints discovered interactively more than twice must be encoded programmatically before the third time. Prompt archaeology is the mechanism that catches constraints that survived two sessions interactively but were never promoted to a script, guide, or skill.
Implements: Issue #146 — Implement prompt archaeology as a post-sprint ritual
Governed by:
AGENTS.md§ Session-Start Encoding Checkpoint — archaeology findings feed the encoding checkpoint for the next sprintMANIFESTO.mdEndogenous-First axiom — session artifacts are the first-order endogenous source
Companion skill: session-retrospective — retrospective harvests this session's lessons; archaeology mines older sessions. They feed each other: retrospective findings accumulate as future archaeology targets.
Foundation documents:
docs/research/scratchpad-architecture-maturation.md— R1 recommendation:docs/sessions/curated archive (the primary persistent archaeology substrate)docs/guides/session-management.md— session lifecycle this skill extends
2. What Is Prompt Archaeology
Prompt archaeology is the practice of systematically reviewing prior session artifacts to recover knowledge that was generated interactively but never encoded into the substrate.
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 · 248 lines · 131 tokens per session scan A 795ed97dc76b
prompt-archaeology is a skill published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 131 tokens to every session and 2,760 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.
prompt-archaeology compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prompt-archaeologyEndogenAI/dogma | Skill | 2 | 2mo ago | Apache-2.0 | A | 131 | Claude Code |
| memoryguardirisxc4/memoryguard | Skill | 3 | 1mo ago | MIT | A | 32 | Claude Code |
| pact-recalljonathanmr22/pact | Skill | 16 | 4mo ago | MIT | A | 16 | Claude Code |
| para-memory-filesCES-Ltd/TitanClip | Skill | 13 | 7mo ago | none | A | 117 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| Profiledanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 108 | Claude Code, Codex |
| knowledge-basewonderwhy-er/DesktopCommanderMCP | Skill | 10k | yesterday | MIT | A | 112 | Claude Code |