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 buildinternet/releases --skill backfilling-sourcesgit clone --depth 1 https://github.com/buildinternet/releasesWrote 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/buildinternet/releases/backfilling-sources)<a href="https://agentmods.dev/skills/buildinternet/releases/backfilling-sources"><img src="https://agentmods.dev/badge/skills/buildinternet/releases/backfilling-sources.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 107 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00094 | $0.02593 |
| Opus 5 | $0.00047 | $0.01296 |
| Sonnet 5 | $0.00019 | $0.00519 |
| Haiku 4.5 | $0.00009 | $0.00259 |
Grade A, and why
backfilling-sources 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 7d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backfilling Sources
Backfill a source's changelog history without the remote extraction inference bill (the update workflow's server-side Haiku / tool-loop passes), using the backfill-source dynamic Workflow (and backfill-sweep for several at once). The Workflow wraps the local-ingest primitives — preflight, fetch + extract, /batch upsert, parity rules — in a deterministic harness that owns the window cap, the budget gate, the dedup, and the safety gate, so the disciplines that are fragile when left to prose are enforced in code.
Local Claude Code only. The Workflow fans out agent() sub-agents and relies on a persistent local filesystem (~/.releases/work/) and the CLI's RELEASES_API_* env. It is not deployed to the managed-agent fleet.
When to use
- A source has substantial history to backfill and running the remote update workflow per window is too expensive.
- A remote fetch burned an extraction loop and wrote 0 releases — extracting locally sidesteps the loop.
When NOT to use
- A clean feed / GitHub source — just add it (
managing-sources) and let cron fetch it. - Inside a managed-agent session — this is local-only.
- A publisher opt-out — the preflight gate refuses it (see below).
Cost contract
- Spends: your Claude Code session tokens for the
agent()sub-agents, hard-capped by the turn'sbudget.total(set with a+Nkdirective). Extraction runs at Sonnet; the mechanical phases (preflight, run-setup, write, validate, report) run at Haiku. - Does NOT spend: no server-side extraction (the update workflow's incremental-Haiku / tool-loop passes), no metered Anthropic API bill.
POST /v1/workflows/updateis never called./batchruns no AI on insert. - Always dry-run first (the default) — it maps + estimates and writes nothing.
- When a dry-run is worth it: on index → detail sources, where it enumerates the per-release pages it would pull and shows how many are new vs already-ingested. For a known single-page source it adds little — it can only confirm shape/reachability, not preview record counts (those need extraction), and the workflow already routes single-page through a lighter recon path (no run-setup or known-URL agent on the way to the estimate). Going straight to
dryRun: falsewith a turn budget is reasonable there.
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.
- 7d ago First seen · 109 lines · 94 tokens per session scan A a81d2cd44802
backfilling-sources is a skill published in the GitHub repository buildinternet/releases (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 94 tokens to every session and 2,593 once invoked, about $0.0005 per session on Opus 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
xquik-social-data
Use Xquik for X and Twitter social data workflows through its public API, SDKs, MCP server, webhooks, and installable agent skill.
releases-cli
Use the releases CLI to search, browse, and read the Releases.sh changelog registry from the terminal — the keyless, agent-friendly peer of the Releases MCP. Activate when the user mentions "releases CLI", runs a releases command, asks how to install it, or wants to look up releases, sources, orgs, collections, or…
releases-mcp
Use when the user asks about recent releases, changelogs, what's new in a library, breaking changes, version updates, or wants to compare products. Activates for questions like "what changed in Next.js 15?", "latest Tailwind releases", "compare Bun vs Deno releases".
analyzing-releases
Analyze release trends across multiple companies to produce competitive intelligence. Use when asked to compare companies, analyze a market segment, identify industry trends, forecast upcoming releases, or answer questions like "what is X shipping lately" or "how does X compare to Y." Also triggers on requests for…
graphql-expert
GraphQL expert for schema design, resolvers, subscriptions, and performance optimization.
openapi-expert
OpenAPI/Swagger expert for API specification design, validation, and code generation.