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 joenandez/spectre --skill spectre-delegategit clone --depth 1 https://github.com/joenandez/spectreWrote 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/joenandez/spectre/spectre-delegate)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-delegate"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-delegate/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/joenandez/spectre/spectre-delegate"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 37 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 38 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.01672 |
| Opus 5 | $0.00025 | $0.00836 |
| Sonnet 5 | $0.00010 | $0.00334 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
spectre-delegate 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
delegate
Purpose
Run Spectre autonomously from inferred scope through TDD, adversarial review, proof, and a draft PR. CI owns verification; never merge/deploy/release.
Inputs
$ARGUMENTS: request, references, optional target, and optional managed feature/root/descendant. Read references fully; if empty, ask and wait. Default:origin/main.
Working Set
- Late-bind checkout, diff, commands, and target.
- Mini eligibility: ≤2 dependency-safe workstreams; no auth/payment/permissions, migration/data-loss, public-contract breakage, concurrency/order/retry, destructive operation, new infrastructure, or unresolved product/UX choice. If ineligible, stop before more mutation: fix →
spectre-fix; feature →spectre-plan.
Feature root contract
- Reuse a managed
FEATURE_ROOTonly when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and followSkill(spectre-feature-root)through DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged. TypefixinitializesKIND=bug; keep{FEATURE_ROOT}/bug-report.mdas its run record.
Outputs + DONE
SCOPE_FILE+ hash: Alignment: inferred · Typefeature|fix· Objective · IN/OUT/ANTI-SCOPE · ACs · Proof Journeys · Assumptions · Target Branch.- Collision-safe
QUICK_PLAN_FILE: Agreed Scope · Research · Approach · 1–2 ordered Workstreams · Success Criteria; map every IN item to implementation/proof. - RED→GREEN commits, affected-check summary, one opposite-runtime-first
Skill(spectre-code_review)before focused proof, committed review/proof artifacts, rebase, tuple,CI: pending, draft PR.
DONE: immutable scope and affected TDD cover the blast radius; one opposite-runtime-first adversarial Skill(spectre-code_review) ran after all implementation/checks and before proof; bounded review/proof repairs are dispositioned; required review and proof artifacts are committed while local lifecycle residue is excluded; draft PR URL returned. No root suite, cleanup meta-flow, merge, deploy, release, or public proof publication. Non-green status is disclosed but does not alone prevent a draft PR; CI merge-gates.
What ships with it
1 file 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.
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.
- 4d ago Changed c7b412e0c355
- 9d ago First seen · 56 lines · 50 tokens per session scan A 76f3bac89bf0
spectre-delegate is a skill published in the GitHub repository joenandez/spectre (158 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,672 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.