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 lynxlangya/techne --skill anchor-reprogit clone --depth 1 https://github.com/lynxlangya/techneWrote 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/lynxlangya/techne/anchor-repro)<a href="https://agentmods.dev/skills/lynxlangya/techne/anchor-repro"><img src="https://agentmods.dev/badge/skills/lynxlangya/techne/anchor-repro/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/lynxlangya/techne/anchor-repro"><img src="https://agentmods.dev/badge/skills/lynxlangya/techne/anchor-repro.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 | $0.00052 | $0.01141 |
| Opus 5 | $0.00026 | $0.00571 |
| Sonnet 5 | $0.00010 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
anchor-repro 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anchor-repro
Force the skipped move in debugging: observe the bug before editing, then prove the fix with the same observation.
Trigger Check
Use this skill when the task is to correct observable behavior that is currently wrong: a failing test, error message, stack trace, regression, crash, hang, wrong return value, wrong render, or "X does Y; it should do Z."
Do not use it for new features, refactors, renames, formatting, docs/copy changes, dependency bumps without a behavioral symptom, or performance work without a measurable probe.
Boundary test: can the wrongness be written as "running X currently produces Y; it should produce Z"? If yes, use this skill and make X the probe seed. If the statement cannot be formed from current information, ask for or find the missing observation before editing.
Forced Procedure
- Capture the symptom and stable anchor. Choose the most stable literal
substring of the observable symptom for
--expect. Omit heap addresses, PIDs, timestamps, temp paths, and wrapped fragments. Use--expectwhenever the symptom has stable text. If no stable text exists,--no-stable-expectis the honest fallback, not an unanchored run; do not use it when stable textual output exists. - Locate, then probe. Read enough code to place the behavior. Pick the
smallest CLI probe that exercises the reported symptom. In workspaces or
monorepos, run from the package with
--cwd <package-dir>, not with acd ... &&convention. If required environment changes matter, encode them inside--shellas one quoted command string such as'VAR=... command'; inherited environment changes are not part of probe identity in v1. - Demonstrate. Run the probe through
scripts/repro_ledger.py run --project <root> --bug <slug> ... -- <command>. Read the failing output and confirm it fails for the reported reason: mechanically,expectMatchedshould be true when--expectwas supplied; procedurally, inspect the tail/context instead of trusting an exit code. - Diagnose against the probe. Test hypotheses with discriminating runs before stacking edits. If a better probe is needed, the new probe starts a new fail -> pass cycle and must be observed failing too.
- Fix.
- Verify with the identical probe identity. Re-run the same execution mode,
argv vector or shell string,
--cwd, and--timeout. Then runscripts/repro_ledger.py close --project <root> --bug <slug>. - Promote when possible. If the target repo has a test suite, promote the probe into a committed regression test. This is encouraged, not a gate.
- Report. Cite the
closeJSON, cite the first repro entry's git evidence, name the strength rung fromreference.md, and carryspeculativewhen the ledger took an unreproduced path.
What ships with it
5 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.
- 9d ago First seen · 113 lines · 52 tokens per session scan A f2864103ae5d
anchor-repro is a skill published in the GitHub repository lynxlangya/techne (105 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 1,141 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…
reqforge-greenkeeper
name: reqforge-greenkeeper description: Used when maintaining the ReqForge repository itself and its release gates fail — pnpm test, pnpm forge-smoke, pnpm sync:discover, adapter drift, skill fixtures, loadouts, or test-demo golden path. Restores a green, synced state with minimal changes. Not for bugs in user apps…
repair-prevention-assessment
A completion gate for fixes and self-repair work. It creates a machine-checkable assessment that separates evidence a current issue is closed from evidence that the fix will remain effective.
app-runtime-verify
Verify a built mobile or app runtime at runtime: run the app (device, emulator, or headless), read the captured runtime output (native logcat, iOS device log, or the Metro/JS console), classify any runtime errors against a per-stack taxonomy, and decide a PASS/FAIL runtime gate for the slice's acceptance behavior. The…
bugfix
Quality bug fixes (P1/P2). Full TDD cycle, branch from master via feature/, no production deploy.