What is run-history-pipeline?

A two-step process that studies a repository's Git history to find recurring failure-handling practices and turn them into reusable skills. Git history is the record of changes made to a code repository over time.

Use it to mine commits for directives, architecture notes, and incidents, then synthesize the incidents into skill files and a plugin manifest. It can resume from the second step.

It helps recover lessons from past incidents instead of leaving them buried in old commits. Clearing context between steps keeps the analysis focused as the work progresses.

run-history-pipeline — Skill for Claude Code and Codex by ProsusAI

Install

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.

Any agent

npx skills add ProsusAI/prism --skill run-history-pipeline

Clone the repo

git clone --depth 1 https://github.com/ProsusAI/prism

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/prosusai/prism/run-history-pipeline/github.svg)](https://agentmods.dev/skills/prosusai/prism/run-history-pipeline)

Your own site

<a href="https://agentmods.dev/skills/prosusai/prism/run-history-pipeline"><img src="https://agentmods.dev/badge/skills/prosusai/prism/run-history-pipeline/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/prosusai/prism/run-history-pipeline"><img src="https://agentmods.dev/badge/skills/prosusai/prism/run-history-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,422 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00052	$0.01422
Opus 5.5	$0.00021	$0.00569
Sonnet 5.5	$0.00010	$0.00284
Haiku 4.5	$0.00005	$0.00142

Measured 2mo ago against content hash 94a075427312, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

run-history-pipeline 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.

skills/run-history-pipeline/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use this skill

Extract failure-mode practices from a repository's git history. Runs two steps in order, clearing context between them (/clear in Claude Code, or clear context in Cursor):

mine-history (/mine-history in Claude Code or @mine-history in Cursor) → reads git log, produces _analysis/directives.md, _analysis/architecture.md, and _analysis/incidents.md
synthesize (/synthesize in Claude Code or @synthesize in Cursor) → reads _analysis/incidents.md, produces _analysis/extracted_skills_history/*/SKILL.md + plugin.json

Supports --from [step-name] to start from a specific step, e.g. /run-history-pipeline --from synthesize (Claude Code) or @run-history-pipeline --from synthesize (Cursor).

Note: This pipeline is optional. If you only want to analyze the codebase's current design (not its history), run /run-analysis-pipeline (Claude Code) or @run-analysis-pipeline (Cursor) instead.

Step 1 — Read pipeline state

Check for _analysis/.history-pipeline-state. Read it if it exists.

State file format:

completed: mine-history
next: synthesize
remaining:
published: false

Parse completed, next, remaining, and published fields. If the file doesn't exist, all steps are pending and mine-history is next.

If --from [step-name] was passed:

Set next to the specified step
Set completed to all steps that precede it in the pipeline order
Set remaining to all steps that follow it
Proceed with this overridden state (do not require a state file to exist)

If the state file shows both steps completed and published: false (or published field absent):

"All 2 pipeline steps are done. Skills are in _analysis/extracted_skills_history/.

Run /curate-skills (Claude Code) or @curate-skills (Cursor) to review and clean up, then /publish-skills (Claude Code) or @publish-skills (Cursor) to create a PR."

Then stop.

If the state file shows all steps completed and published: true:

Read the full file on GitHub · 143 lines

Changes

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 · 143 lines · 52 tokens per session scan A 94a075427312

Subscribe to this mod's changes

run-history-pipeline is a skill published in the GitHub repository ProsusAI/prism (20 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,422 once invoked, about $0.0002 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 2026-08-30.

Building agents Git and workflow

run-history-pipeline next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
run-history-pipelineProsusAI/prism	Skill	20	4mo ago	Apache-2.0	A	52	Claude Code, Codex
merge-batchdiegosouzapw/OmniRoute	Skill	83k	5d ago	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	yesterday	MIT	A	20	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	yesterday	MIT	A	51	Claude Code
comet-githubrpamis/comet	Skill	3.3k	yesterday	MIT	A	72	Claude Code, Codex
release-helperSahir619/fable-method	Skill	2.3k	1mo ago	MIT	A	43	Claude Code