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 alexmond/alexmskills --skill progress-channelgit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/alexmond/alexmskills/progress-channel)<a href="https://agentmods.dev/skills/alexmond/alexmskills/progress-channel"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/progress-channel.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 5.1 | $0.00149 | $0.03926 |
| Opus 5 | $0.00075 | $0.01963 |
| Sonnet 5 | $0.00030 | $0.00785 |
| Haiku 4.5 | $0.00015 | $0.00393 |
Grade B, and why
progress-channel scanned grade B with 2 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Use it as the whole status line, in `~/.claude/settings.json`: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s 'localhost:7717/jobs?session=<id>' # one session's work How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
progress-channel
Work that takes minutes is usually reported by whatever the agent happens to print — a carriage-returned counter in one terminal. That fails three ways: the only way to learn the state is to re-ask (pure overhead), the counter can lie (a stale fragment reads as a stall; submission-order iteration pins it at 0), and work handed to another system has no representation at all. This skill makes a shared progress channel the default for all three.
The discipline
- Register anything expected to exceed ~10s — a sweep, a backgrounded
command, a call that hands work to another system and returns early.
progress forecast <name>answers "how long has this taken before" prior to starting; if history says minutes, register. - Never answer a progress question by re-polling and narrating. The
answer is the channel: the live page at
http://127.0.0.1:7717/,watchin a terminal, orlistonce. Register, then get on with something else. - External work gets a
mirrorwatcher — one small process polling the foreign system into the same channel, exiting when the work is idle. One list, whatever the source.
Architecture
The thing that serves the progress page is the tracker. A stdlib-only
Python daemon (http.server, no dependencies) binds 127.0.0.1:7717
($PROGRESS_PORT overrides), holds live jobs in memory — single writer,
so there is no store or locking at all — and serves the HTML view at /,
JSON at /jobs, and forecasts at /forecast?name=.
- Producers auto-spawn it: the first
Jobbrings the daemon up if it isn't running; binding the port is the single-instance lease. Nothing to install or supervise. - Only the learning data is persisted: finished runs append to
~/.claude/progress/history.jsonl(cat/jq-able;$PROGRESS_HOMEoverrides the directory). Live state is memory-only on purpose — if the daemon restarts, producers re-register on their next flush; a reboot kills the jobs anyway. - A job never fails because the tracker is sick: if the daemon can't be reached or spawned, the job degrades to a warn-once untracked no-op.
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.
- yesterday Changed · +21 lines eb821ad718cd
- 2d ago Changed · +126 lines scan A → B a89b24a3fdcc
- 8d ago First seen · 170 lines · 149 tokens per session scan A b29b3ef9138d
progress-channel is a skill published in the GitHub repository alexmond/alexmskills (6 stars, last pushed today), licensed MIT. It adds 149 tokens to every session and 3,926 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, 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
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
relay
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
token-optimizer
Reduce Claude Code token consumption and API costs without sacrificing output quality. Use this skill whenever the user mentions high costs, expensive sessions, token waste, burning through credits, wanting to use Haiku instead of Opus, model routing, MAXTHINKINGTOKENS, extended thinking cost, CLAUDECODESUBAGENTMODEL…
korean-character-count
Count Korean text deterministically with exact grapheme, line, and byte contracts for self-intros and form limits.