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 adtn0810/truestack --skill truestack-dependency-managementgit clone --depth 1 https://github.com/adtn0810/truestackWrote 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/adtn0810/truestack/truestack-dependency-management)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-dependency-management"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-dependency-management/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/adtn0810/truestack/truestack-dependency-management"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-dependency-management.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 | $0.00227 | $0.02617 |
| Opus 5 | $0.00113 | $0.01308 |
| Sonnet 5 | $0.00045 | $0.00523 |
| Haiku 4.5 | $0.00023 | $0.00262 |
Grade A, and why
truestack-dependency-management 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 11d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-dependency-management
Own the policy and lifecycle of everything the app pulls from a registry — what gets added, how
fast it updates, how it's pinned and verified, when a CVE blocks a build, and what ships in the
SBOM. On a self-hosted single server there is no blast-radius isolation: a poisoned install script
runs with the box's full ambient credentials (deploy keys, cloud metadata, .env). Accuracy and
stability over chasing latest; honesty over a green scan you didn't verify.
Read project memory first — CLAUDE.md is auto-loaded (Principles + Boundaries); consult
.ai/memory/ for the stack, package manager, lockfiles, registries, and any pin/policy decisions
already recorded. If none exists, run truestack-project-memory. Keep the code↔memory tally balanced:
adding a dependency, changing a pin, or setting a cooldown/scanner policy is a decision — record it
in the same change.
Auto-research, don't recall. Never assert a CVE, GHSA, severity, fix-version, license, or SLSA
detail from memory — version- and advisory-specific facts go stale. Ground every claim in
authoritative sources at decision time (OSV/GHSA, the registry, NIST SSDF SP 800-218 / C-SCRM SP
800-161, SPDX, slsa.dev). Adopting a new dependency or a cooldown override is a real ingestion
decision — route a consequential one through truestack-architecture-planning's approval gate. (The enforced
PreToolUse gate in hooks/ does not stop a plain npm/pip install; it only catches a
postinstall that pipes a remote payload into a shell — so the add-time cooldown + triage here is the
real control, not the hook.)
Where this skill sits (seams to respect): this skill owns the ongoing dep policy and
lifecycle. truestack-ci-and-delivery SHA-pins its own GitHub Actions and runs the scanner step in
CI — but the policy that step enforces (pin mode, cooldown, the fail-on bar, the SBOM artifact)
is this skill's. truestack-quality-control runs the one-shot SAFETY pass on a given change (including
"this bump introduces a known CVE"); truestack-application-security owns the security DESIGN/discipline;
this skill owns the standing dependency posture between changes. truestack-mcp-integration owns
untrusted tool-output; the PreToolUse hook governs agent actions — both are different layers.
truestack-observability redacts PII in telemetry; truestack-data-privacy owns the privacy policy — neither is
license/SBOM. truestack-backend-development justifies why a dep is needed at code time; this skill
governs whether and how it enters and stays.
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.
- 11d ago First seen · 141 lines · 227 tokens per session scan A 60dcc6065c13
truestack-dependency-management is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 227 tokens to every session and 2,617 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.