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 fledgeling-co/fledgeling-plugins --skill reckongit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/reckon)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/reckon"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/reckon/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/fledgeling-co/fledgeling-plugins/reckon"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/reckon.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 | $0.00579 | $0.05442 |
| Opus 5 | $0.00290 | $0.02721 |
| Sonnet 5 | $0.00116 | $0.01088 |
| Haiku 4.5 | $0.00058 | $0.00544 |
Grade A, and why
reckon 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 10d 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 — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reckon
A reckoning is a settling of accounts. This one settles what a project said it would do against what anybody actually established, and reports the difference in a form somebody can schedule.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It converts the adjudication step's categorical scopes into denominators the ledger prints, and forbids any figure in the report that did not come from ledger.json or the gate's exit code. Other models skip it.
The failure this exists to prevent
A remaining-work list is built by filtering: take everything, drop what is done, report the rest. The filter is where it fails, because "not done" and "not known" are different things that both look like absence.
The campaign this skill was written against is the ordinary case, not a bad one. Fifty-eight designed cases: 25 reached a verdict, 32 did not — blocked on a dead credential, on a state with no hook to force it, on a surface that could only be reached by signing the owner out of their only account. Fifteen stated requirements: two observed, thirteen standing on the project's own account of itself. Filter that to failures and you get a tidy list of 14 things, and 43% coverage disappears without leaving a mark.
Regulated verification calls the fix a closed-world reconciliation: freeze
the baseline, enumerate every requirement, planned case and open defect, and
partition that universe into verified, remaining, exception, or
not-applicable. An item absent from the partition does not make the
determination complete — it makes it invalid. That is the whole design here,
and scripts/reckon.py enforces it with an exit code rather than asking you
to be careful. Sources in references/evidence.md.
The partition
Eight classes, and every entity on both sides lands in exactly one. Full
definitions, the legality table and worked examples are in
references/partition.md; this is the shape.
What ships with it
8 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.
- 10d ago First seen · 425 lines · 579 tokens per session scan A 61786e7dc383
reckon is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 579 tokens to every session and 5,442 once invoked, about $0.0029 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 2026-09-04.
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.
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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.