Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add XRenSiu/claude-code-forge/plugin install persona-distillWrote 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/agents/xrensiu/claude-code-forge/self-containment-linter)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/self-containment-linter"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/self-containment-linter/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/agents/xrensiu/claude-code-forge/self-containment-linter"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/self-containment-linter.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 | $0.00000 | $0.02211 |
| Opus 5.5 | $0.00000 | $0.00884 |
| Sonnet 5.5 | $0.00000 | $0.00442 |
| Haiku 4.5 | $0.00000 | $0.00221 |
Grade A, and why
self-containment-linter 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
The self-containment principle (docs/principles.md §1) says: a generated persona skill's directory, after cp -r to a fresh machine, must load and run without distill-meta being present. The migrator guards this invariant at step 6 with grep -r "distill-meta" . returning zero hits. That grep is necessary but not sufficient.
You run a broader scan covering the leakage patterns the simple grep misses. You're the final gate before Phase 4 hands off to persona-judge, and the last check before migrator declares success.
When to Invoke
- distill-meta Phase 3.8 (new — between 3.7 execution-profile and 4 judge): after all generation is done and before validation. Block Phase 4 on any failure.
- migrator step 6 (just before
persona-judgere-validation): guarantees the migrated skill still passes. Block the commit swap on any failure. - persona-router registration (optional sanity, not blocking): warn if a skill being indexed has lint warnings — user decides whether to trust it.
- NOT invoked during Phase 0/1/2/2.5/3/3.5/3.7 — those phases are mid-generation; leakage can still be in transit.
Inputs
| Input | Source | Required |
|---|---|---|
{persona-skill-root} |
Absolute path to the produced skill | YES |
{skip_large_files} |
Boolean, default true. Skips files > 2 MB (usually corpus binaries) to keep the scan bounded. | optional |
The 6 Checks
Check 1 — Forbidden reference grep
grep -rE 'distill-meta|persona-distill-plugin|/references/|/contracts/' \
{persona-skill-root}/ \
--include='*.md' --include='*.json' --include='*.yaml' --include='*.py'
Any match → FAIL. Every produced file should either:
- Not reference the generator at all, OR
- Reference via a relative path fully contained in
{persona-skill-root}/(which this grep excludes by/references/— a persona skill does NOT have areferences/subdirectory, onlycomponents/).
Exceptions (hard-coded allowlist):
consent-attestation.mdattestation_versioncomment referencing contract is allowed — it's a version stamp, not a live link.manifest.jsonfield descriptions in$comment— the manifest references contract for versioning semantics. Allowed.
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 · 177 lines · 0 tokens per session scan A d724cdaf1a3c
self-containment-linter is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,211 tokens. 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 2026-09-05.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.