stigmergy: Skill for Claude Code

.claude/skills/land-a-change/SKILL.md

land-a-change is a skill for Claude Code from sturlese/stigmergy. It costs 26 tokens per session (472 once invoked), scanned A, original, Apache-2.0.

A workflow guide for completing changes in a Stigmergy software project, including defects, new features, refactoring, and documentation updates.

In plain words
What is it for?
Use it to land a Stigmergy change, check whether a public contract needs special handling, and identify when an independent security or architecture review is needed.
Why use it?
It helps choose the right review and implementation steps, while keeping code, tests, specifications, and related repositories consistent.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is sturlese/stigmergy's own configuration. It tells Claude Code how to work on stigmergy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stigmergy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sturlese/stigmergy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sturlese/stigmergy/main/.claude/skills/land-a-change/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sturlese/stigmergy

Made for: Claude Code.

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.

agentmods badge for land-a-change

README.md
[![agentmods](https://agentmods.dev/badge/skills/sturlese/stigmergy/land-a-change/github.svg)](https://agentmods.dev/skills/sturlese/stigmergy/land-a-change)
Your own site
<a href="https://agentmods.dev/skills/sturlese/stigmergy/land-a-change"><img src="https://agentmods.dev/badge/skills/sturlese/stigmergy/land-a-change/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.

agentmods 80×15 button for land-a-change

Your own site · 80×15
<a href="https://agentmods.dev/skills/sturlese/stigmergy/land-a-change"><img src="https://agentmods.dev/badge/skills/sturlese/stigmergy/land-a-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 472 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00472
Opus 5 $0.00013 $0.00236
Sonnet 5 $0.00005 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 12d ago against content hash 822211ab206a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

land-a-change 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 12d 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.

.claude/skills/land-a-change/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Land a Stigmergy change

Read CLAUDE.md and the active implementation specification before changing behavior. Use code and tests as the authority when older prose conflicts with them.

Select the workflow

Change Workflow
Observable defect or false executable promise squad:fix
New capability or moved product surface squad:define then squad:build
Behavior-preserving restructuring squad:refactor
Documentation-only correction ordinary change closed by squad:review

Read squad:breaking-change before changing a public tool contract, schema, persisted format, or event shape. The current test deployment uses a clean cut: do not add migration, compatibility, or rollback machinery unless a later specification explicitly requires it.

Use an independent security/architecture auditor when the change touches ACL decisions, identity or token resolution, queue leasing or retries, Git gates, evidence storage, answer verification, or any read path that can reveal restricted knowledge.

Keep both repositories coherent

Changes to the filing contract normally affect both the platform and the knowledge repository. Update the live librarian skill, thin linter/authorship launchers, templates, control files, and workflows with the platform code and fixtures. The platform package owns the executable contract; the knowledge repository must not carry a second implementation.

Model-owned knowledge paths are committed by the trusted writer identity and pushed through the librarian GitHub App. Operator-owned controls and documentation use the normal contributor identity. Both repositories must pass their own CI.

Completion

  1. Run focused tests, Ruff, and the complete keyless suite.
  2. Run the proportional final-validation workflow and resolve every finding.
  3. Commit and push both repositories with the required identities; wait for green CI.
  4. Deploy every affected process group.
  5. Follow validate-deployment for live evidence when the image or cross-system contract changed.

Read the full file on GitHub · 50 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.

  1. 12d ago First seen · 50 lines · 26 tokens per session scan A 822211ab206a

Subscribe to this mod's changes

land-a-change is a skill published in the GitHub repository sturlese/stigmergy (9 stars, last pushed 17d ago), licensed Apache-2.0. It adds 26 tokens to every session and 472 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 2026-08-31.

Related

Other skills, from other repositories