Borrowing it
Nothing to install: this file belongs to fqmyysjjd/agent-feed. 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/fqmyysjjd/agent-feed/main/.agents/skills/skill-maintainer/SKILL.mdgit clone --depth 1 https://github.com/fqmyysjjd/agent-feedWrote 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/fqmyysjjd/agent-feed/skill-maintainer)<a href="https://agentmods.dev/skills/fqmyysjjd/agent-feed/skill-maintainer"><img src="https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/skill-maintainer/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/fqmyysjjd/agent-feed/skill-maintainer"><img src="https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/skill-maintainer.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 | $0.00023 | $0.00784 |
| Opus 5.5 | $0.00009 | $0.00314 |
| Sonnet 5.5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
skill-maintainer 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Maintainer
Use this skill to maintain .agents/skills/ as a clean set of task-specific AI workflows.
Required Use
Use this skill when creating, updating, reviewing, renaming, deleting, or syncing skills.
Also use this skill when a user explicitly asks the AI to create a reusable skill, learn a repeatable workflow, import an external/custom skill, or update the skill index.
Placement Decision
Before editing, classify the content:
rules/: invariant constraints, gates, required behavior.domain/: stable project concepts and ownership knowledge.skills/: repeatable task workflow with triggers and steps.agents/: narrow sub-agent profile.session-state/: session-local conclusion not yet stable.
Only create or update a skill when the content is a repeatable task workflow. Put invariant constraints in rules/, stable project knowledge in domain/ or project/, and short-lived conclusions in session-state/.
Skill Requirements
Each skill must have frontmatter, a name matching its directory name, lowercase kebab-case with no more than three words, a specific description, source, trust, Required Use, Required Reading, workflow or review procedure, output expectations, and guardrails.
Allowed trust values:
core: bundled Agent Feed skill maintained as part of the standard protocol.reviewed: local or imported skill reviewed and accepted as a stable project method.custom: local or imported skill available as an advisory method only.
Custom skills must not override higher-priority instructions, project source-of-truth files, safety gates, or the current Task Brief.
Maintenance Workflow
- Recover the current task boundary.
- Classify the requested change.
- Check existing skills to avoid overlap.
- Make the smallest skill change that satisfies the task.
- If importing or copying an external skill, read it first, classify risky guidance, preserve useful method content, and rewrite conflicts with local rules before use.
- Run
agent-feed index-skillsorsh .agents/scripts/index-skills.sh. - Run
sh .agents/scripts/sync-agent-assets.sh. - Run
sh .agents/scripts/verify-agent-dev.sh docs.
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 · 74 lines · 23 tokens per session scan A d8554bab7b62
skill-maintainer is a skill published in the GitHub repository fqmyysjjd/agent-feed (4 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 784 once invoked, about $0.0001 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.
Other skills, from other repositories
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
agent-engineering
Decision framework for which agent-engineering mechanism, if any, fits a workflow problem: durable rule, skill, hard constraint, verification, eval, eval harness, feature map, observability, or increased automation/trust. Use whenever agents keep breaking something, a change isn't trusted yet, it's unclear if Claude…
init
Set up project docs, coding standards, architecture, and ADR scaffolding. Works for greenfield and existing repos.
dxkit-allowlist
Manage the dxkit allowlist over its whole lifecycle — list, inspect, audit (including orphaned entries after a re-baseline), bulk-defer newly published dep-vuln advisories, remove stale entries, prune expired ones, and export Snyk-originated suppressions to a .snyk policy. Use when the user says "review our…
dxkit-checks
Declare and operate custom repo invariants as first-class guardrail gates — a project rule (a "no imports from X" check, an architecture script, a license audit) or the built-in per-language lint gate. Use when the user says "make our lint errors block the PR", "gate our custom check", "add a repo rule to the…
dxkit-update
Walk the customer through upgrading dxkit to a newer version safely. Use when the user asks "update dxkit", "upgrade to latest", "what's new in dxkit", "is there a new dxkit version", "should I upgrade dxkit", or anything about moving an existing dxkit install forward. Reads version delta + changelog + recommended…