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 lugassawan/swe-workbench --skill comms-contextgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/comms-context)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/comms-context"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/comms-context/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/lugassawan/swe-workbench/comms-context"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/comms-context.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 | $0.00051 | $0.00786 |
| Opus 5.5 | $0.00020 | $0.00314 |
| Sonnet 5.5 | $0.00010 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
comms-context 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to invoke
Auto-loads when the caller references:
- Slack permalink:
<workspace>.slack.com/archives/<channel>/p<timestamp>. - PagerDuty incident URL:
<subdomain>.pagerduty.com/incidents/<id>. - PagerDuty incident ID: a bare incident ID mentioned alongside a PagerDuty context clue (e.g. "PagerDuty incident
PD-4521"), when a PagerDuty MCP tool (mcp__pagerduty__*) is reachable in-session. - Free-text on-call signal: text describing a page, on-call escalation, or Slack thread reference.
If no reference is present, exit cleanly.
Adapters
Slack permalink
- Trigger: Slack permalink URL (
<workspace>.slack.com/archives/<channel>/p<timestamp>). - Fetch:
mcp__slack__get_permalink_threadwith the channel and timestamp parsed from the URL (aspirational — this plugin ships no Slack MCP integration; this recipe activates only if the user has one connected). Resolve the permalink to a channel + timestamp, then fetch the root message and its thread replies. - Extract → block fields: message author plus every distinct thread replier → Participants; message and reply timestamps in chronological order → Timeline; if the thread reaches a visible resolution or decision, summarize it, else "ongoing" → Status; the permalink itself → Source.
- Degrade: If no
mcp__slack__*tool is reachable, emitcomms-context: Slack MCP unavailable; proceeding without context.Never fabricate thread content or participants.
PagerDuty incident
- Trigger: PagerDuty incident URL (
<subdomain>.pagerduty.com/incidents/<id>), or a bare incident ID paired with a PagerDuty context clue — gated on a reachablemcp__pagerduty__*tool (no other skill claims PagerDuty IDs, so this trigger is unconditional once the URL or a PagerDuty-labeled ID is present; no cross-skill disambiguation is needed here). - Fetch:
mcp__pagerduty__get_incidentwith the incident ID or URL (aspirational — this plugin ships no PagerDuty MCP integration; this recipe activates only if the user has one connected). Fetch incident details, the escalation timeline, and current on-call responders. - Extract → block fields: assignee plus on-call responders → Participants; triggered/acknowledged/resolved timestamps in order → Timeline; current incident status (triggered/acknowledged/resolved) → Status; incident URL → Source.
- Degrade: If no
mcp__pagerduty__*tool is reachable, emitcomms-context: PagerDuty MCP unavailable; proceeding without context.Never fabricate incident status or timeline. On auth error, surface the raw error. On empty/404, say so; do not guess.
What ships with it
1 file 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.
- 1mo ago First seen · 49 lines · 51 tokens per session scan A 49f9d65a374f
comms-context is a skill published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 786 once invoked, about $0.0002 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
cmd/gerp
Performs native command line terminal operations for gerp subsystem. Use when doing matrix cli executions, or when the user mentions cobra, terminal operators, viper configs, or the gerp binary.
java-clean-comments
Enforces comment and Javadoc hygiene in Java — no commented-out code, no author or ticket metadata, no comments restating the code, and Javadoc that documents contracts rather than repeating signatures. Use when writing or reviewing Java comments and Javadoc, and when the code shows commented-out blocks, TODO or FIXME…
py-clean-comments
Use when writing, fixing, editing, or reviewing Python comments and docstrings. Enforces Clean Code principles—no metadata, no redundancy, no commented-out code. Also trigger on: commented-out code blocks, TODO/FIXME banners, author/ticket/date metadata in comments, docstrings that no longer match the code, redundant…
ts-clean-comments
Use when writing, fixing, editing, or reviewing TypeScript comments and TSDoc. Enforces Clean Code principles—no metadata, no redundancy, no commented-out code. Also trigger on: commented-out code blocks, TODO/FIXME banners, author/ticket/date metadata in comments or TSDoc, TSDoc that no longer matches the code…
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
relations
OPS on-demand: This skill should be used when the user asks to "who do I owe a reply", "relationship…