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 AlexZio00/sovereign-skills --skill full-auditgit clone --depth 1 https://github.com/AlexZio00/sovereign-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/alexzio00/sovereign-skills/full-audit)<a href="https://agentmods.dev/skills/alexzio00/sovereign-skills/full-audit"><img src="https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/full-audit/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/alexzio00/sovereign-skills/full-audit"><img src="https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/full-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00205 | $0.07081 |
| Opus 5.5 | $0.00082 | $0.02832 |
| Sonnet 5.5 | $0.00041 | $0.01416 |
| Haiku 4.5 | $0.00020 | $0.00708 |
Grade A, and why
full-audit 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 6d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Audit — Exhaustive Area Review
Dominant Variable
Accuracy of the coverage claim — the word "exhaustive" ships with a method label or it doesn't ship at all. The moment an unreviewed area gets reported as reviewed, this skill has failed its own purpose.
Trigger
/full-audit [area]· "audit everything" · "exhaustive audit" · "full audit" · "double-check everything"- Default mode on any of the above:
AUDIT_ONLY. These are analysis requests, not execution requests — see Execution Modes below. Advancing toPROPOSEorAPPLY_APPROVEDin the same invocation requires the user to say so explicitly (e.g. "audit everything and apply the fixes").
Discard If
- Single file / single question needs checking → use a regular code review instead
- The goal is a harness-maturity score against a fixed checklist → use a fixed-checklist scoring tool instead
- The goal is a single docs-vs-code drift check → too narrow a scope for this
- An identical-scope full audit finished within the last 7 days and nothing has changed → just diff against the existing coverage map instead
Key Assumptions
- Target area is agreed in Phase 0 — if not, don't start without an area table.
- Deterministic sweeping (scripts/grep) is available for the target — if not, skip Phase 1 and never claim "exhaustive" from Phase 2 (LLM review) alone.
- A prior coverage map can shrink the scope via diff — if not, do a full re-scan.
Execution Modes: AUDIT_ONLY / PROPOSE / APPLY_APPROVED
This skill keeps analysis and execution in separate, explicitly-named modes. A trigger phrase like "audit everything" or "analyze this" selects a mode — it does not, by itself, authorize any file write.
| Mode | When active | What runs | Writable scope |
|---|---|---|---|
AUDIT_ONLY (default) |
Any bare audit/analysis trigger, with no separate execution request | Phase 0-3 (scope, deterministic sweep, content review, judgment) + Phase 5 (coverage map) | None — audited files are read-only. No Edit/Write to any target file, protected or not. Only audit artifacts may be written (scratch scripts, canary staging, coverage map, recall ledger). |
PROPOSE |
User asks for fix proposals (after an AUDIT_ONLY pass, or up front) |
AUDIT_ONLY output + a listed fix/addition bucket (Phase 4 framing, nothing applied) |
None — still read-only, output is a proposal list |
APPLY_APPROVED |
User explicitly approves specific items or the fix bucket as a whole ("apply these items", "apply the fix bucket") | Applies only the items the user named as approved | Limited to the approved items. A protected path (see "Protected paths" under Safety Layers) is reachable only here, only for that one named item, and only by drafting the edit plus an apply script for the user to run themselves — the model has no path to lift a deny rule (the deny rule lives in the same settings file it protects). |
What ships with it
13 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.
- .claude-plugin/plugin.json 621 B
- agents/openai.yaml 142 B
- scripts/canaries/clean/account_repo.py 239 B runs code
- scripts/canaries/clean/settings_loader.py 227 B runs code
- scripts/canaries/README.md 2.2 KB
- scripts/canaries/seeded/billing_client.json 306 B
- scripts/canaries/seeded/billing_client.py 202 B runs code
- scripts/canaries/seeded/user_lookup.json 248 B
- scripts/canaries/seeded/user_lookup.py 195 B runs code
- scripts/canary_mix.py 6.4 KB runs code
- scripts/canary_score.py 8.3 KB runs code
- scripts/test_canary_mix.py 6.5 KB runs code
- scripts/test_canary_score.py 7.1 KB runs code
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.
- 6d ago Changed · +10 lines ffbd703e412f
- 18d ago Changed · +1 lines c7b8e3f14f70
- 1mo ago Changed · +6 lines a60679c3125b
- 1mo ago Changed · +1 lines 04b6f5113993
- 1mo ago Changed · +20 lines · +44 tokens per session 7594d1612f22
- 1mo ago First seen · 155 lines · 161 tokens per session scan A 14acb7b43c7d
full-audit is a skill published in the GitHub repository AlexZio00/sovereign-skills (149 stars, last pushed 7d ago), licensed MIT. It adds 205 tokens to every session and 7,081 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 2026-08-30.
Other skills, from other repositories
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
incident-response
Incident management lifecycle — triage, communicate, mitigate, postmortem. Three modes — new (start incident), update (status update), postmortem (blameless RCA report).
review-diff
Scan git diffs for project-specific anti-patterns. Triggers on: 'scan diff', 'check diff', 'anti-pattern check', 'pattern scan', 'review changes'.