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.
npx agentmods add skills/motiful/skill-forge/maintenance-rulesnpx skills add motiful/skill-forge --skill maintenance-rulesgit clone --depth 1 https://github.com/motiful/skill-forgeWhat 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 | $0.00074 | $0.02439 |
| Opus 5 | $0.00037 | $0.01220 |
| Sonnet 5 | $0.00015 | $0.00488 |
| Haiku 4.5 | $0.00007 | $0.00244 |
Grade A, and why
maintenance-rules 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 2d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-forge Maintenance Rules
Constraints and procedures for maintaining the skill-forge repository.
Execution Procedure
maintain(trigger) → updated | no_change
if "platform registry" in trigger:
update_platform_registry()
update_downstream() # SKILL.md Fix Phase, README install, Detection logic
if "community tools" in trigger:
update_community_tools()
if change proposed:
run_decision_test() # 7 criteria → accept | reject
verify_constraints() # each MUST's parenthesized method
run_consistency_checks()
update_changelog() # max 5, trim oldest
after significant changes:
run_self_governance() # 4 steps
Constraints
- MUST run Decision Test (7 criteria below) before accepting any change
- MUST NOT push SKILL.md body over 500 lines
- MUST keep SKILL.md ↔ README ↔ references terminology consistent
- MUST add References section entry when adding new reference files
- MUST update "Dependencies" table in README when SKILL.md dependencies or setup.sh changes
- MUST NOT include content that fails the Positional Test (see references/skill-format.md)
- MUST verify reference files follow three-layer format (frontmatter + EP + aligned Content)
- MUST keep examples in standard-defining references generic — no skill-forge-specific labels in universal patterns
- MUST verify SKILL.md pseudocode function names align with sub-module EP entry signatures (run: grep function names from references/ EPs, diff against SKILL.md pseudocode calls)
- MUST verify lossless delegation when moving inline criteria to a sub-module: map every deleted parent line to a sub-module EP line. Unmapped criteria → add to sub-module first, then remove from parent (run: diff parent before/after, match each removed line to a sub-module line)
- MUST verify every defined standard has a corresponding enforcement check in Validation (Structure, Quality, or Publishing). A standard without a check is dead weight — either add the check or remove the standard
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.
- 2d ago First seen · 122 lines · 74 tokens per session scan A 66eb76cd8859
maintenance-rules is a skill published in the GitHub repository motiful/skill-forge (45 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 2,439 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
localization-design
Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
design-debt-audit
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).
design-impact-reporting
Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).
motion-system
Define motion tokens — durations, easing vocabulary, and reduced-motion handling — for consistency product-wide. Use when standardising motion across a system. For crafting one specific animation, use animation-principles (interaction-design).