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 ailiheizi/workflow-to-skill --skill rss-digestgit clone --depth 1 https://github.com/ailiheizi/workflow-to-skillWrote 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/ailiheizi/workflow-to-skill/rss-digest)<a href="https://agentmods.dev/skills/ailiheizi/workflow-to-skill/rss-digest"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/rss-digest/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/ailiheizi/workflow-to-skill/rss-digest"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/rss-digest.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 | $0.00023 | $0.00456 |
| Opus 5.5 | $0.00009 | $0.00182 |
| Sonnet 5.5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
rss-digest 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 2mo 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.
What it actually says
Use the configured Weft Daily intelligence workflow Publication for this
request. The user may provide one or more HTTP(S) RSS or Atom URLs, a focus
topic, and a maximum highlight count. Pass those values in the Publication's
input object, preserving the source URLs exactly. Do not fetch feeds with a
different tool, invent feed entries, or recreate the workflow locally.
After starting the Publication, use mcp__weft__get_work_snapshot with the
returned runId until the Run reaches succeeded or failed, the user or
Harness cancels, 30 snapshot calls have been made, or five minutes have
elapsed. Keep polling with the returned eventCursor when available, and do
not poll more often than the tool's suggested interval or every two seconds.
Before each additional call, honor any observed cancellation. On a bound,
report the Run as still running or unverified with its runId; do not submit a
replacement Run. Report the actual Run status, generated Artifact names, and
source diagnostics. A successful answer must preserve each item's source feed,
publication time when present, and original article URL; link to the Artifacts
rather than copying an unverified digest into the response.
If one feed fails, continue when the Weft Run succeeds and clearly identify the
failed URL and diagnostic. If the Run fails or the snapshot cannot be read,
stop and report the real failure and runId; do not retry blindly or claim a
digest was produced. A new run may be requested only after the user confirms
the changed input or recovery action.
If the initial submission outcome is uncertain, do not submit again. Reconcile
only with a returned runId, operation identifier, or external receipt. When
none is available, report the outcome as unknown and stop.
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.
- 2mo ago First seen · 36 lines · 23 tokens per session scan A e1fa294a12c1
rss-digest is a skill published in the GitHub repository ailiheizi/workflow-to-skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 456 once invoked, about $0.0001 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
agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
aiwg-language-map
AIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
steward
Provide provider capability awareness and route commands by answering what the current provider supports natively vs must emulate.
infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly.