What is prune-source?

A guided command for removing an outdated source store from a registry file. It first checks whether the source is stale and whether other projects depend on it, then comments it out for one scheduled cycle before deleting it.

Use it to retire unreachable, abandoned, replaced, or persistently broken source stores from `sources/supported-stores.json`, while checking consumers and recording the reason.

Deleting a source immediately can break downstream projects or hide the reason for its removal. The staged process makes the change reviewable and reversible for a period.

prune-source — Command for GitHub Copilot by fabioc-aloha

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.

Clone the repo

git clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_Mall

Made for: GitHub Copilot.

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/commands/fabioc-aloha/alex_skill_mall/prune-source/github.svg)](https://agentmods.dev/commands/fabioc-aloha/alex_skill_mall/prune-source)

Your own site

<a href="https://agentmods.dev/commands/fabioc-aloha/alex_skill_mall/prune-source"><img src="https://agentmods.dev/badge/commands/fabioc-aloha/alex_skill_mall/prune-source/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/commands/fabioc-aloha/alex_skill_mall/prune-source"><img src="https://agentmods.dev/badge/commands/fabioc-aloha/alex_skill_mall/prune-source.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 710 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	$0.00027	$0.00710
Opus 5	$0.00014	$0.00355
Sonnet 5	$0.00005	$0.00142
Haiku 4.5	$0.00003	$0.00071

Measured today against content hash b99b8037006f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prune-source 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 today.

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.

.github/prompts/prune-source.prompt.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prune-source

Remove a source store from the Mall's registry. Runs staleness-discipline classification first, then a downstream-impact check, then the two-step reversible removal (comment-out → observe → delete).

Steps

Apply staleness-discipline to classify the proposed removal. Confirm at least one staleness signal fires (link unreachable, upstream archived, no activity 18+ months, license drift, replaced by superior alternative, persistent breakage).
Downstream-impact check: the Mall is consumed by downstream projects via pinned upstream refs. Surface the proposed removal in the catalog-refresh PR description so reviewers can flag any downstream impact. If a known consumer depends on plugins from this store, give them notice before the second-step deletion.
Reversible removal (step 1 of 2): Comment out the entry in sources/supported-stores.json rather than deleting. Add a line above it: // pruned-pending: YYYY-MM-DD reason: <reason>.
Commit [behaviour] prune source (pending): <name> — <reason>.
Push. Let one weekly cron cycle run with the source commented out. Verify the catalog refresh PR shows the expected removal (store missing from catalog/stores/, plugin count drops by the right amount, no other unintended diffs).
Reversible removal (step 2 of 2): After one clean cycle, delete the commented-out entry. Update the comment to // pruned: YYYY-MM-DD reason: <reason> (delete: YYYY-MM-DD) as an archival note above the surrounding entry.
Commit [behaviour] prune source (delete): <name>.

Re-add procedure (if needed later)

If a pruned store revives, do not silently re-add. Run /add-source from scratch — past acceptance does not transfer; the scorecard must re-evaluate against current state.

Boundaries

Do not delete a source store entry in one commit. The two-step (comment-out → observe → delete) is the safety net against silent catalog breakage.
Do not prune without the downstream-impact check. Consumers depending on the store should get notice before deletion.
Do not prune plugin-mall itself. The self-entry is constitutional to this Mall's design; removing it would break the catalog's ability to surface first-party plugins.
Do not prune for "I don't like the maintainer" or other subjective reasons. The staleness signals are the bar; document the firing signal in the commit message.

Read the full file on GitHub · 37 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.

today First seen · 37 lines · 27 tokens per session scan A b99b8037006f

Subscribe to this mod's changes

prune-source is a command published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 710 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 2026-09-08.

Commits Git and workflow agentic-ai ai-assistant ai-skills best-practices github-copilot knowledge-base

prune-source

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/prune-source

Steps

Re-add procedure (if needed later)

Boundaries

What this file has done since we first saw it

Other commands, from other repositories

apex-git-commit

validate-pr-description

cm

triage-github

wtfp:contribute

cp