Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pjt222/agent-almanacnpx agentmods add skills/pjt222/agent-almanac/audit-discovery-symlinksWrote 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/pjt222/agent-almanac/audit-discovery-symlinks)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/audit-discovery-symlinks"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/audit-discovery-symlinks/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/pjt222/agent-almanac/audit-discovery-symlinks"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/audit-discovery-symlinks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to high
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 →
- high Tool Misuse · line 273 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 278 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 286 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 290 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 291 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 132 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.
- medium Rogue Agent · line 196 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.
- medium Agent Snooping · line 355 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00095 | $0.04225 |
| Opus 5.5 | $0.00038 | $0.01690 |
| Sonnet 5.5 | $0.00019 | $0.00845 |
| Haiku 4.5 | $0.00010 | $0.00422 |
Grade A, and why
audit-discovery-symlinks 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 1mo 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audit-discovery-symlinks
When to Use
- After adding new skills, agents, or teams to the almanac
- After a repository rename or move that may have broken absolute symlinks
- When slash commands or agents are not found in Claude Code
- As a periodic health check to catch drift between registries and discovery paths
- When onboarding a new project that should discover shared almanac content
Do NOT use for creating the initial symlink hub from scratch. See the symlink-architecture guide for first-time setup.
Inputs
| Parameter | Type | Required | Description |
|---|---|---|---|
almanac_path |
string | No | Absolute path to agent-almanac root. Auto-detected from .claude/ symlink targets or cwd if omitted |
scope |
enum | No | project, global, or both (default: both) |
fix_mode |
enum | No | report (default: audit only), auto (fix all safe issues), interactive (prompt before each fix) |
Procedure
Step 1: Identify Almanac Path
Locate the agent-almanac root directory.
# Auto-detect from current project's .claude/agents symlink
ALMANAC_PATH=$(readlink -f .claude/agents 2>/dev/null | sed 's|/agents$||')
# Fallback: check if cwd is the almanac
if [ -z "$ALMANAC_PATH" ] || [ ! -f "$ALMANAC_PATH/skills/_registry.yml" ]; then
if [ -f "skills/_registry.yml" ]; then
ALMANAC_PATH=$(pwd)
fi
fi
# Fallback: check global agents symlink
if [ -z "$ALMANAC_PATH" ] || [ ! -f "$ALMANAC_PATH/skills/_registry.yml" ]; then
ALMANAC_PATH=$(readlink -f ~/.claude/agents 2>/dev/null | sed 's|/agents$||')
fi
echo "Almanac path: $ALMANAC_PATH"
Got: ALMANAC_PATH points to a directory containing skills/_registry.yml, agents/_registry.yml, and teams/_registry.yml.
If fail: If auto-detection fails, ask the user for the almanac_path input. The almanac root is the directory containing skills/, agents/, teams/, and their registries.
Step 2: Inventory Registries
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.
- 1mo ago First seen · 376 lines · 95 tokens per session scan A 629463002488
audit-discovery-symlinks is a skill published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed 5d ago), licensed MIT. It adds 95 tokens to every session and 4,225 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
audit-pr
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
execute-phase
Step executor for units whose triage (unit-lane) decided which steps the unit needs. Implements one triaged step (or all remaining steps), with frozen acceptance, step-local gates, commits, red-gate repair, and diff-size guard. BREAKING: replaced PLAN.md/TASKS.md/progress.md/ACCEPTANCE.md with the unit doc's Tasks…
fold-findings
Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row folded: yes updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".
init-workspace
Adapt the workflow scaffold to a new repository or add only missing substrate blocks to an existing install. Every install, hook, and overwrite needs explicit consent. Triggers: "init-workspace", "set up agentic workflow", "upgrade workflow scaffold".
product-audit
Audit the whole product across code, quality, process, docs, roadmap, and tooling; it owns the repo-wide bug hunt, security research, and broken-version investigation (scoped and budgeted per dimension, as distinct from review-change's change-scoped review). Persist one severity-ranked, F-numbered report with…
review-change
Review a change with only applicable internal axes, classify every finding, persist fix-now work, and return one evidence-backed decision. Findings only; --adversarial N uses isolated reviewers; --synthesize fuses supplied reviewer tables. Triggers: "review-change", "review this change", "adversarial review".