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 tomzx/agents --skill extract-colleague-decisionsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/extract-colleague-decisions)<a href="https://agentmods.dev/skills/tomzx/agents/extract-colleague-decisions"><img src="https://agentmods.dev/badge/skills/tomzx/agents/extract-colleague-decisions/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/tomzx/agents/extract-colleague-decisions"><img src="https://agentmods.dev/badge/skills/tomzx/agents/extract-colleague-decisions.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 | $0.00120 | $0.04539 |
| Opus 5.5 | $0.00048 | $0.01816 |
| Sonnet 5.5 | $0.00024 | $0.00908 |
| Haiku 4.5 | $0.00012 | $0.00454 |
Grade A, and why
extract-colleague-decisions 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 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.
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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Colleague Decisions
Answers a recurring question: "What did my colleagues actually decide today?" A day of Slack produces many messages, most of them chatter, acknowledgements, and questions, with a handful of real decisions inside. This skill searches Slack for each colleague's authored messages in a day, then reads them and pulls out the decisions, so you can catch up on what changed without reading every thread.
The judgement is the point: telling a decision from chatter is a reading task, not a keyword match.
slackx conversations search only gets the messages in front of you; you decide what counts.
Prerequisites
SLACK_TOKEN(andSLACK_COOKIEfor xoxc/web tokens) in.env, found by searching up from the working directory. Source it before invokingslackx.COLLEAGUESin.env: a comma-separated list of Slack usernames (e.g.alice.smith,bob.jones). Resolve it with~/.agents/scripts/get-env COLLEAGUES.slackxon PATH; install if missing:if ! command -v slackx &>/dev/null; then git clone https://github.com/TomzxCode/slackx /tmp/slackx uv tool install /tmp/slackx fijqfor filtering the search JSON.- Optional:
JEV_ENDPOINTandJEV_TOKENin the environment, only for theclassify_message.pyaccelerator. The script reads them (or--endpoint/--token) and has no host baked in. Skip them if you classify by reading.
Workflow
1. Resolve inputs
Determine the target day: the argument if given (YYYY-MM-DD or yesterday), otherwise today.
Compute the window (see the slackx skill for why Slack's day operators are bracketed this way):
TARGET=2026-09-18 # or: date +%Y-%m-%d
PREV=$(date -d "$TARGET - 1 day" +%Y-%m-%d)
NEXT=$(date -d "$TARGET + 1 day" +%Y-%m-%d)
Resolve the colleagues and source credentials:
set -a; source .env; set +a
COLLEAGUES=$(~/.agents/scripts/get-env COLLEAGUES)
If COLLEAGUES is empty, stop and tell the user to set it.
Do not guess handles.
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.
- 22d ago Changed · -69 lines f8002f5b9ed9
- 25d ago Changed a36d0844f9e6
- 28d ago Changed · +4 lines ea16dfec8a0c
- 1mo ago Changed · +38 lines 2879b2923bea
- 1mo ago First seen · 350 lines · 120 tokens per session scan A 8a4162e5dace
extract-colleague-decisions is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 4,539 once invoked, about $0.0005 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 2026-09-20.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.