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 revenantworks/claude-skills --skill revenantworks-foundation-scoutwrightgit clone --depth 1 https://github.com/revenantworks/claude-skillsWrote 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/revenantworks/claude-skills/revenantworks-foundation-scoutwright)<a href="https://agentmods.dev/skills/revenantworks/claude-skills/revenantworks-foundation-scoutwright"><img src="https://agentmods.dev/badge/skills/revenantworks/claude-skills/revenantworks-foundation-scoutwright/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/revenantworks/claude-skills/revenantworks-foundation-scoutwright"><img src="https://agentmods.dev/badge/skills/revenantworks/claude-skills/revenantworks-foundation-scoutwright.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 | $0.00202 | $0.02843 |
| Opus 5.5 | $0.00081 | $0.01137 |
| Sonnet 5.5 | $0.00040 | $0.00569 |
| Haiku 4.5 | $0.00020 | $0.00284 |
Grade A, and why
revenantworks-foundation-scoutwright 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 2d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
revenantworks-foundation-scoutwright
history in CHANGELOG.md · sources and parity register in SOURCES.md · Apache-2.0 (LICENSE)
The Claude platform changes every week, and a lot of it never reaches an announcement. scoutwright reads the official feeds, the docs and the community since the last time it looked, and writes a dated change report where every change that touches this setup lands as affects X, change file Y, owning skill Z. Its adopt list feeds a skill currency sweep. It never changes anything itself: it reports, and the owning skill acts.
Workflow: ledger → read sources → diff → classify and tag → map to this setup → report and adopt rows → ledger update
Turn shape
- What affects this setup comes first. Breaking or security changes that touch a file here lead the report; platform news that touches nothing here follows; quiet sources are one line.
- Every change row carries its evidence. Class, area tag, source URL, first-seen date, and (when it touches this setup) the affected file and the owning skill. A row without a source URL does not ship.
- Nothing unread is hidden. A source that failed, timed out, sits behind a block or needs the owner's capture is listed by name with what happened. Unread is never "no change".
Load budget
| Entry | Reads |
|---|---|
sweep, since |
source-map.md, diffing.md, relevance-map.md, output-format.md |
watch <area> |
source-map.md (that area's rows), diffing.md, relevance-map.md, output-format.md |
adopt |
output-format.md (adopt rows), relevance-map.md |
fit |
fit.md, relevance-map.md §1, source-map.md (the item's rows) |
bench |
bench.md, source-map.md §2a |
sources, refresh |
source-map.md, diffing.md (route health) |
pack.md only on boundary doubt. researchscribe's hard-sources.md is read through that skill,
never copied here.
Optional mods: references/mods.md, only when their data is present.
What ships with it
60 files 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.
- CHANGELOG.md 3.5 KB
- evals/adopt-names-file/case.yaml 430 B
- evals/adopt-names-file/graders/affects-line.md 281 B
- evals/adopt-names-file/graders/fires.md 170 B
- evals/adopt-names-file/graders/names-file.md 105 B
- evals/adopt-names-file/graders/names-key.md 97 B
- evals/adopt-names-file/graders/no-secret.md 131 B
- evals/adopt-names-file/graders/owner.md 121 B
- evals/adopt-names-file/prompt.md 588 B
- evals/adopt-names-file/resources/CHANGELOG.md 159 B
- evals/adopt-names-file/resources/settings.json 303 B
- evals/adopt-names-file/scaffold.sh 242 B runs code
- evals/bench-verdict-rows/case.yaml 304 B
- evals/bench-verdict-rows/graders/fires.md 160 B
- evals/bench-verdict-rows/graders/injection.md 435 B
- evals/bench-verdict-rows/graders/long-tail.md 132 B
- evals/bench-verdict-rows/graders/supply-chain.md 383 B
- evals/bench-verdict-rows/graders/verdicts.md 726 B
- evals/bench-verdict-rows/prompt.md 2.8 KB
- evals/changelog-new-versions/case.yaml 368 B
- evals/changelog-new-versions/graders/breaking.md 109 B
- evals/changelog-new-versions/graders/exact-set.md 397 B
- evals/changelog-new-versions/graders/fires.md 162 B
- evals/changelog-new-versions/graders/first-seen.md 106 B
- evals/changelog-new-versions/graders/new-942.md 112 B
- evals/changelog-new-versions/graders/new-943.md 86 B
- evals/changelog-new-versions/prompt.md 479 B
- evals/changelog-new-versions/resources/CHANGELOG.md 403 B
- evals/changelog-new-versions/resources/ledger.json 206 B
- evals/changelog-new-versions/scaffold.sh 242 B runs code
- evals/docs-page-diff/case.yaml 431 B
- evals/docs-page-diff/graders/added.md 104 B
- evals/docs-page-diff/graders/fires.md 176 B
- evals/docs-page-diff/graders/injection-finding.md 354 B
- evals/docs-page-diff/graders/removed.md 106 B
- evals/docs-page-diff/graders/undocumented.md 127 B
- evals/docs-page-diff/prompt.md 568 B
- evals/docs-page-diff/resources/CHANGELOG.md 69 B
- evals/docs-page-diff/resources/llms-new.txt 421 B
- evals/docs-page-diff/resources/llms-old.txt 252 B
- evals/docs-page-diff/scaffold.sh 242 B runs code
- evals/fit-card-no-tier-edit/case.yaml 425 B
- evals/fit-card-no-tier-edit/graders/card-fields.md 776 B
- evals/fit-card-no-tier-edit/graders/fires.md 174 B
- evals/fit-card-no-tier-edit/graders/no-tier-edit.md 339 B
- evals/fit-card-no-tier-edit/graders/trial-proposed.md 596 B
- evals/fit-card-no-tier-edit/graders/verdict-words.md 160 B
- evals/fit-card-no-tier-edit/prompt.md 502 B
- evals/fit-card-no-tier-edit/resources/ledger.md 558 B
- evals/fit-card-no-tier-edit/resources/models-overview.md 564 B
- evals/fit-card-no-tier-edit/resources/tiers.md 232 B
- evals/fit-card-no-tier-edit/scaffold.sh 242 B runs code
- evals/nearmiss-apply-build-row/graders/stays-quiet.md 195 B
- evals/nearmiss-apply-build-row/prompt.md 294 B
- evals/nearmiss-claude-md/graders/stays-quiet.md 171 B
- evals/nearmiss-claude-md/prompt.md 223 B
- evals/nearmiss-schedule-routine/graders/stays-quiet.md 184 B
- evals/nearmiss-schedule-routine/prompt.md 303 B
- evals/nearmiss-vector-db/graders/stays-quiet.md 189 B
- evals/nearmiss-vector-db/prompt.md 237 B
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.
- 2d ago Changed · +3 tokens per session 3f33c7fd7edf
- 12d ago Changed · +4 lines · +35 tokens per session ee7f7dbe9b6c
- 15d ago First seen · 160 lines · 164 tokens per session scan A 16f3c96be583
revenantworks-foundation-scoutwright is a skill published in the GitHub repository revenantworks/claude-skills (2 stars, last pushed today), licensed Apache-2.0. It adds 202 tokens to every session and 2,843 once invoked, about $0.0008 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 2026-10-11.
Other skills, from other repositories
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
stakeholder-map
Build a stakeholder map using a power/interest grid, identify communication strategies per quadrant, and generate a communication plan. Use when managing stakeholders, preparing for a launch, aligning cross-functional teams, or planning stakeholder engagement.
brainstorm-experiments-existing
Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods. Use when validating assumptions, testing feature ideas cheaply, or planning product experiments.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.