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/rsenna/rs-agent-plugin/fix-mapped-issuenpx skills add rsenna/rs-agent-plugin --skill fix-mapped-issuegit clone --depth 1 https://github.com/rsenna/rs-agent-pluginWrote 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/rsenna/rs-agent-plugin/fix-mapped-issue)<a href="https://agentmods.dev/skills/rsenna/rs-agent-plugin/fix-mapped-issue"><img src="https://agentmods.dev/badge/skills/rsenna/rs-agent-plugin/fix-mapped-issue.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01348 |
| Opus 5 | $0.00036 | $0.00674 |
| Sonnet 5 | $0.00015 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
fix-mapped-issue 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 today.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Mapped Issue
Steps 4–6 of the issue lifecycle: implement the mapped tasks, ship them via the
pull-request process, then update and close the issue. Assumes
map-issue-to-tasks already produced tasks/issue-<n>-<slug>.md. If that file
doesn't exist, run map-issue-to-tasks first.
Reuses the sibling skills' scripts (this plugin's other skills, installed as
siblings of this one under the same skills root — resolve these relative to
wherever this fix-mapped-issue skill itself was loaded from):
../pull-request-process/pr.sh(branch/push/PR/threads)../map-issue-to-tasks/issue.sh(closefor the final comment)
Portability — read the project's specifics first
From the project's AGENTS.md: the base branch and the
quality gate command + coverage bar (e.g. what-about:
mix precommit --cover, ≥ 90% — see AGENTS.md:23–30). Pass the base branch as
BASE= to pr.sh.
Do this (per task, until the issue is done)
- Pick the next task from
tasks/issue-<n>-*.md: the next unchecked box, respecting dependency order. If the file predates the checkbox convention (any heading with no leading- [ ]/- [x]), retrofit a checkbox onto every heading before picking —- [x]for tasks the file already notes as done/merged,- [ ]for the rest — so the "next unchecked box" rule has something to operate on. If it's a 🔒 ask-first gate (new dependency, DB migration, CI/secret change), pause and get explicit approval before starting. - Implement via the
incremental-implementationandtest-driven-developmentskills. New or changed behaviour must be described by tests (behaviour-asserting, not coverage-padding). - Ship it via the
pull-request-processskill — one task ≈ one PR:pr.sh start(thencdinto the worktree path it prints) → implement/commit → run the gate → runpull-request-processstep 3's exactrequesting-code-reviewpass and fix what it flags → re-run the gate if any code changed →REVIEWED=1 pr.sh push→pr.sh open→ STOP (never merge). Then handle review threads per that skill. - After the maintainer/bots merge, tick the task's checkbox in
tasks/issue-<n>-*.md(- [ ]→- [x]) and append the merged PR link to that task's heading line in exactly this form:— ✅ merged (#<n>)— a fixed syntax so later automation can parse it reliably. If a task shipped across more than one PR, list every merged PR in that same parenthetical, in merge order, comma-separated (— ✅ merged (#9, #12)); never drop an earlier PR link when a later one for the same task lands. This edit is itself a change to a tracked file, so commit and ship it through the samepull-request-processflow as any other change — never push it straight to the base branch. Either give it its own small PR or fold it into the next task's branch if you're about to start that task anyway. Then move to the next task. Repeat until every task is merged.
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.
- today Changed · +18 lines 12715c8b0995
- 3d ago First seen · 83 lines · 73 tokens per session scan A 90c08af1d74a
fix-mapped-issue is a skill published in the GitHub repository rsenna/rs-agent-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 1,348 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 2026-08-31.
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…