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 skills add scharissis/polako --skill implement-issuegit clone --depth 1 https://github.com/scharissis/polakoWrote 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/scharissis/polako/implement-issue)<a href="https://agentmods.dev/skills/scharissis/polako/implement-issue"><img src="https://agentmods.dev/badge/skills/scharissis/polako/implement-issue/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/scharissis/polako/implement-issue"><img src="https://agentmods.dev/badge/skills/scharissis/polako/implement-issue.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 | $0.00000 | $0.15977 |
| Opus 5.5 | $0.00000 | $0.06391 |
| Sonnet 5.5 | $0.00000 | $0.03195 |
| Haiku 4.5 | $0.00000 | $0.01598 |
Grade A, and why
implement-issue scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
already sits inside this run's grant; none of it needs `curl`, `sleep` How it starts
The opening of the file, as written. The whole thing — 1,040 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement GitHub issue #$issue
This run gets one turn
Ending your turn ends the process. There is no later turn to come back to and
nothing that can wake you — not a Monitor, not a scheduled wake-up, not a
background job you meant to poll, not a subagent whose result you never
awaited. Whatever the worktree holds the moment you stop is all the run leaves
behind: uncommitted edits, an unpushed branch, no PR. To the supervisor that is
indistinguishable from a run that produced nothing, so a perfectly good issue
gets parked. Interactively every one of those waits works, which is exactly why
this needs saying.
So anything whose result you need is waited for inside this turn, however long it takes. Never end a turn intending to resume. A measurement worth taking is worth blocking on; one not worth blocking on should be dropped rather than deferred.
Waiting is not the same as going quiet, though. A supervisor kills and resumes
a run that emits nothing for -stall — fifteen minutes by default — so a wait
longer than that is polled from here, in repeated calls that keep the run
visibly alive, rather than spent inside one call a watchdog cannot tell from a
hang. Poll it slowly — a check every minute or two. Each check is a fresh
turn that reloads the whole late-session context, so polling faster costs a
lot and buys nothing. Backgrounding the slow thing is fine; what is not is
the turn ending while it is still outstanding.
Polling is only for work still running when you look. A Skill call that
hasn't returned yet needs none: the harness holds the turn until it returns,
so a ListAgents or Bash: true heartbeat beside it is waste. But a return
is not proof the work behind it is done, however finished its prose reads —
the skill may still have subagents running in the background. So before
trusting a Skill call's result, check ListAgents: nothing related still
running means done; anything still running is backgrounded work, polled
slowly as above. Phase 3 step 2c says how the review gate checkpoints what
arrives while it waits.
What ships with it
4 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.
- 22d ago Changed · +106 lines 0064ad092c22
- 24d ago Changed · -8 lines 60ea8a1977f3
- 26d ago Changed · +56 lines d5764af89e39
- 27d ago Changed · +241 lines 15d85493494d
- 28d ago Changed · +116 lines · -15 tokens per session a69848b230b3
- 1mo ago Changed · +162 lines 00b890d1aa5f
- 1mo ago First seen · 367 lines · 15 tokens per session scan A 24dbcbe1f9aa
implement-issue is a skill published in the GitHub repository scharissis/polako (1 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 15,977 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
pi-review-gated-delivery
Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.
rhiza-fix
Read this repo's open issues, triage them, and open one pull request per issue that can be fixed without a judgement call. Issues that need a decision, or that look stale or superseded, are reported with a recommendation rather than guessed at.
rememora-developer
Use this skill when working on Rememora development tasks such as picking approved tickets, planning implementations, writing code in isolated worktrees, running validation, and preparing pull requests. This is the Codex-facing equivalent of the Claude Code rememora-developer subagent.
gitlab-mr
GitLab merge request operations. ALWAYS use this skill when user wants to: (1) list merge requests, (2) view MR details, (3) create new MRs, (4) approve/merge MRs, (5) checkout MR branches, (6) add notes/comments, (7) rebase MRs.