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/sandovalrr/project-context/project-issuesnpx skills add sandovalrr/project-context --skill project-issuesgit clone --depth 1 https://github.com/sandovalrr/project-contextWhat 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 | $0.00087 | $0.01279 |
| Opus 5 | $0.00044 | $0.00639 |
| Sonnet 5 | $0.00017 | $0.00256 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
project-issues 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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Issues
Use the host-local project registry to select the correct issue workspace, account, and project for the current Git repository. Treat the configured context as authoritative for external issue writes.
Resolve Context First
- Call
resolve_project_contextonce when issue work begins. - Resolve again when the working repository changes or when configuration is edited.
- State the selected provider, target, and authenticated identity before preparing a write.
- Stop before a write if the repository, provider, credential, or identity is not configured or does not match.
Use project-context resolve --cwd <path> only when the project_issues MCP tools are unavailable.
Route Deterministically
Provider selection follows this order:
- An explicit issue URL.
- A qualified reference such as
linear:ENG-123,github:#318, orjira:OPS-42. - One unique configured identifier pattern.
- The configured default provider.
Never infer a provider from issue wording. Never retry a failed provider operation against another provider. List and search only the default provider unless the user explicitly names a provider or requests all configured providers.
Read Issues
- Use
list_issuesfor canonical status filters and direct subissue listing,search_issuesonly for title/description text, andget_issuefor a single issue. Request relation expansion only when parent, subissue, blocking, related, or duplicate information is needed. - Use
list_issue_commentswhen the user needs the discussion on one issue. Results are newest first and target-scoped;truncated: truemeans older comments were omitted. This tool does not return field history or a full activity timeline. - Use
get_issue_capabilitiesbefore creating an issue or whenever valid labels, priorities, issue types, canonical statuses, defaults, or presets are unknown. Pass returned option values unchanged. - Use
search_issue_optionswhen a label, priority, issue type, cycle, or milestone capability points to it, when its inline catalog is truncated, or when a large catalog needs narrowing. Pass the returned value unchanged. - Treat capability
operationsas authoritative. An empty option list does not mean arbitrary values are valid; checkacceptsCustomValues,defaultValue, anddiscoveryTool. - Treat
optionsTruncated: trueas incomplete. Do not claim an unlisted value is invalid solely because it is absent from a truncated catalog. - Treat option-search
truncated: truethe same way: narrow the query rather than guessing or rejecting an absent value. - Never select a creation preset silently. Present relevant named presets and let the user choose.
- Never simulate status filtering by searching for text such as "in progress".
- Treat
truncated: trueas incomplete. Surface missing or ambiguous mapping errors instead of weakening the requested filter. - For an unconfigured repository, explain that host-local context is missing. Conversational or explicitly supplied context may support a read, but do not treat it as write authorization.
- GitHub pull requests are outside this skill even though the GitHub Issues API can return them.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 75 lines · 87 tokens per session scan A 36d37d62d017
project-issues is a skill published in the GitHub repository sandovalrr/project-context (1 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 1,279 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…