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 ALTEN-group/coding-pal --skill control-guardgit clone --depth 1 https://github.com/ALTEN-group/coding-palWrote 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/alten-group/coding-pal/control-guard)<a href="https://agentmods.dev/skills/alten-group/coding-pal/control-guard"><img src="https://agentmods.dev/badge/skills/alten-group/coding-pal/control-guard/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/alten-group/coding-pal/control-guard"><img src="https://agentmods.dev/badge/skills/alten-group/coding-pal/control-guard.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 | $0.00078 | $0.00583 |
| Opus 5.5 | $0.00031 | $0.00233 |
| Sonnet 5.5 | $0.00016 | $0.00117 |
| Haiku 4.5 | $0.00008 | $0.00058 |
Grade A, and why
control-guard 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 3d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Control Guard
Deterministic control-integrity guard. It reads a unified diff and fails when the change weakens the checks that judge it. It also enforces the bug rule on a commit range. Agents run it, they never change it.
When to Use This Skill
- An agent finished a change or a gate fix and must prove it did not weaken a control to get a pass.
- CI scans the pull request diff before any other control result is trusted.
- A production defect is fixed and the failing check must be committed before the fix.
Path resolution
Resolve references/ and scripts/ relative to this skill's install directory (the folder that contains this SKILL.md). If the skill was installed under .agents/skills/control-guard/ or .claude/skills/control-guard/, use that base path.
Workflow
- Read
references/control-guard-contract.mdfor the eight rules (R1 to R8), the configuration, and the bug rule. - Scan the change. Commit or stage new files first: untracked files are not scanned.
# Working tree and commits since the merge base with main
node scripts/control-guard.mjs --git origin/main
# A saved diff, or JSON output for an agent
node scripts/control-guard.mjs --diff change.diff --json
- Each finding is printed as
RULE file:line message. Treat a nonzero exit as a failure: remove the weakening (restore the test, the threshold, the step) and fix the real fault instead. Do not editcontrol-guard.json, workflows, or installed skills. Only the Architect passes--allow-pathfor a control change. - For a defect fix, check the commit order, then prove the new check fails without the fix with the
test-probeskill:
node scripts/bug-rule.mjs --git origin/main..HEAD --defect "#123"
Done When
scripts/control-guard.mjsexits with code 0 on the final diff.- For a defect fix,
scripts/bug-rule.mjsexits with code 0: a tests-only commit precedes the first commit that changes non-test files. - No
--allow-pathwas used by an agent, and no protected file was edited.
What ships with it
6 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.
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.
- 3d ago First seen · 46 lines · 78 tokens per session scan A 2d34dfea9f67
control-guard is a skill published in the GitHub repository ALTEN-group/coding-pal (5 stars, last pushed 5d ago), licensed MIT. It adds 78 tokens to every session and 583 once invoked, about $0.0003 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 2026-10-14.
Other skills, from other repositories
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.