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 BrentFarris/echo --skill fossil-provider-performancegit clone --depth 1 https://github.com/BrentFarris/echoWrote 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/brentfarris/echo/fossil-provider-performance)<a href="https://agentmods.dev/skills/brentfarris/echo/fossil-provider-performance"><img src="https://agentmods.dev/badge/skills/brentfarris/echo/fossil-provider-performance/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/brentfarris/echo/fossil-provider-performance"><img src="https://agentmods.dev/badge/skills/brentfarris/echo/fossil-provider-performance.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 | $0.00050 | $0.00918 |
| Opus 5.5 | $0.00020 | $0.00367 |
| Sonnet 5.5 | $0.00010 | $0.00184 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
fossil-provider-performance 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 5d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fossil provider performance contract (internal/sourcecontrol/fossil)
fossil changes flag rules (verified empirically against fossil 2.29)
--hashis required for change detection. Without it, fossil relies on recorded mtime/size and silently misses same-size edits (e.g.xyz→wxy), even with a fresh mtime. Never drop--hashfrom achangescall whose result feeds change detection.fossil changesis O(checkout size) no matter how few paths it is scoped to (~25µs/file measured; a 1-file scoped call costs the same as a full scan).fossil info/finfostay O(1) (~30ms). This asymmetry drives the whole architecture: interactive requests must never wait on achangesspawn.fossil extrasis redundant:changes --differalready lists extra (untracked) files with theEXTRAcode. Never add a separateextrasspawn.
Cache architecture (status.go)
repositoryStatecarries a status snapshot cache (keyed to the revision token) and a change-records cache, plus single-flight background refresh (queueStatusRefresh, throttled byrefreshMinInterval) that pushessource_control_statusvia the notifier (wired bysourcecontrol.Service.RegisterthroughNotifyingProvider).- Caching is gated on
cachingAllowed(active subscription): without a subscriber there are no file-event invalidations, so every status recomputes. This keeps direct-disk-mutation semantics (integration tests, external edits with no watcher) correct. Status()= recovery → fresh cache (≤2s) → stale-while-revalidate (serve last-known + background refresh + push) → synchronous compute (cold).computeStatusdouble-checks the cache undercomputeMuso concurrent callers share one checkout scan.rawStatus/rawStatusPathsanswer from the records cache (TTL 5s) when fresh;pathIsConflicted(diff hot path) does too. Partial scoped results are never cached.afterMutation(actions.go, in the Action defer after the revision bump): checkpoint-only actions (protect/unprotect/hunks) rebuild the snapshot from cached records + the just-written manifest (rebuildStatusCache) so the next status is instant; checkout-changing actions invalidate everything (the service's async post-action push recomputes).InvalidateWorkspacebumps the revision and drops caches; recovery of an interrupted protected commit invalidates too (journal existed).service.Actionpushes the post-action status asynchronously (goroutine) — never put a full VCS scan back on the action request path.
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.
- 5d ago First seen · 37 lines · 50 tokens per session scan A 3d09df19273b
fossil-provider-performance is a skill published in the GitHub repository BrentFarris/echo (11 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 918 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 2026-10-21.
Other skills, from other repositories
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
update-nanoclaw
Transactionally update a customized NanoClaw checkout from official upstream without exposing live mounted source, with fork-safe skill refresh, mutable-state snapshots, migration gates, exact-code upgrade markers, detected service restart, health verification, and automatic local rollback. Use for routine merge…
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
github-auth
Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.
github
Use gh as the primary interface for GitHub data and actions. Keep this skill focused on basic operations and command safety, not maintainer triage strategy.