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/explyt/spring-plugin/github-issue-managernpx skills add explyt/spring-plugin --skill github-issue-managergit clone --depth 1 https://github.com/explyt/spring-pluginWhat 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 | $0.00097 | $0.03757 |
| Opus 5 | $0.00048 | $0.01878 |
| Sonnet 5 | $0.00019 | $0.00751 |
| Haiku 4.5 | $0.00010 | $0.00376 |
Grade A, and why
github-issue-manager 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue Manager (explyt/spring-plugin)
Create or find an issue in explyt/spring-plugin from a user description, following the repository issue forms and label conventions.
Critical constraints
- Work only with the GitHub repository
explyt/spring-plugin. If the user names another repository, stop and ask them to use a workflow configured for that repository. - Never create a new issue when an open (or relevant closed) issue with the same core outcome already exists.
- Before creating an issue, always do light codebase research and a similar-issue search.
- Do not implement, deep-review, or refactor code: research only enough for a good title, body, labels, and template choice.
- Pick labels from the live repository label list (
gh label list --repo explyt/spring-plugin); never invent label names. - Verify every label exists before passing it to
gh, including labels named in this skill and labels declared by the issue forms.gh issue createfails outright on an unknown label. Check with:gh label list --repo explyt/spring-plugin --limit 200 --json name --jq '.[].name'and match exactly. - Do not trust the
labels:field in.github/ISSUE_TEMPLATE/*.yml. A form may declare a label that no longer exists in the repository (verified:plugin-bugdoes exist in the live label list and is applied to filed bugs, whilefeature-request, declared by the feature form, is absent, so that form silently applies nothing). Treat the forms as the source of truth for body structure only, and verify each declared label againstgh label listbefore relying on it. - Use the live label catalog and the module/feature mapping below; the static list is a synchronization aid, not a substitute for refreshing GitHub. The repository has
type:internalfor engineering tasks, while form categories useplugin-bug,compatibility, andquestion. Use a matchingin:<module>area label when one exists, plus only relevant feature/topic labels. - Never pass component dropdown values such as
Navigation gutterorAutocompletionas labels: they are form fields, not GitHub labels. Reference examples: #25/#44/#268 (inspection,in:spring-core), #118 (inspection,in:spring-core,properties), #142 (inspection,in:spring-web). - If a needed label genuinely does not exist, file without it and say so in the report; never create labels, invent an
in:<module>label, or substitute a similar-looking name. - If issue creation is blocked (permissions, auth, missing tooling), return the ready-to-create title/body/labels and the exact blocker instead of retrying.
- When creating or proposing a new issue, always append as the final body line:
_Created automatically by github-issue-manager skill._ - Never include secrets, tokens, private customer data, or local absolute paths in an issue body.
- For delegated codebase research use
call_ask_agent; the subagent must return a complete summary inline (no artifact files needed for this light research).
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 · 318 lines · 97 tokens per session scan A 07ce14268292
github-issue-manager is a skill published in the GitHub repository explyt/spring-plugin (160 stars, last pushed 3d ago), licensed Apache-2.0. It adds 97 tokens to every session and 3,757 once invoked, about $0.0005 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
spring-ecosystem-docs
Spring Boot 4.x + Framework 7.x — auto-configuration, DI, AOP, MVC, WebFlux, Security, Data JPA/MongoDB/Redis.
analyze-external-methods
Analyze an OpenTaint scan's dropped external methods and decide which of them are propagators and optionally sinks. Use when a dropped-external-methods.yaml needs classification for dropped method type.
create-rule
Author and verify an OpenTaint rule. Use whenever a rule creation is needed.
create-test-project
Create an OpenTaint test project with positive/negative samples for verifying a rule or approximation. Use when a rule or approximation needs a test project to check against.
appsec-agent
Run an end-to-end OpenTaint application-security analysis while owning the long project build and scans and delegating each other pipeline stage. Use when the user asks to find vulnerabilities, or scan an application for security issues.
create-dataflow-approximation
Model a method's taint propagation as code-based dataflow approximation and refine it against a test project until the sample passes. Use for a dropped method that requires code-based approximation.